Move libmp3lame into the lame directory

This is where it would be in the original library structure and makes the CMakeLists.txt a tad cleaner.
2025-12-12 15:46:25 +01:00 · 2020-05-26 02:05:43 -05:00
parent d738d35a7b
commit 51507ecdf8
63 changed files with 23 additions and 1365 deletions
--- a/lib-src/lame/libmp3lame/i386/Makefile.am
+++ b/lib-src/lame/libmp3lame/i386/Makefile.am
@@ -0,0 +1,73 @@
+## $Id: Makefile.am,v 1.28 2013/06/12 09:16:29 rbrito Exp $
+
+AUTOMAKE_OPTIONS = foreign
+
+DEFS = @DEFS@ @CONFIG_DEFS@
+
+ECHO ?= echo
+
+nasm_sources = \
+	choose_table.nas \
+	cpu_feat.nas \
+	fft3dn.nas \
+	fftsse.nas
+
+if HAVE_NASM
+noinst_LTLIBRARIES = liblameasmroutines.la
+liblameasmroutines_la_SOURCES = $(nasm_sources)
+liblameasmroutines_la_DEPENDENCIES = $(nasm_sources:.nas.lo)
+am_liblameasmroutines_la_OBJECTS = \
+	choose_table$U.lo \
+	cpu_feat$U.lo \
+	fft3dn$U.lo \
+	fftsse$U.lo
+endif
+
+noinst_HEADERS = nasm.h
+
+INCLUDES = @INCLUDES@ -I$(top_srcdir)/libmp3lame/@CPUTYPE@
+
+SUFFIXES = .nas .lo
+
+EXTRA_liblameasmroutines_la_SOURCES = $(nasm_sources)
+
+CLEANFILES = \
+	choose_table.o.lst \
+	choose_table.lo.lst \
+	cpu_feat.o.lst \
+	cpu_feat.lo.lst \
+	fft3dn.o.lst \
+	fft3dn.lo.lst \
+	fftsse.o.lst \
+	fftsse.lo.lst
+
+EXTRA_DIST = \
+	fft.nas \
+	fftfpu.nas \
+	ffttbl.nas \
+	scalar.nas
+
+NASM = @NASM@
+NASMFLAGS=@NASM_FORMAT@ -i $(top_srcdir)/libmp3lame/@CPUTYPE@/
+
+.nas.o: $< nasm.h
+	$(NASM) $(NASMFLAGS) $< -o $@ -l $@.lst
+
+.nas.lo: $< nasm.h
+	$(ECHO) '# Generated by ltmain.sh - GNU libtool 1.5.22 (1.1220.2.365 2005/12/18 22:14:06)' >$@
+	$(ECHO) "pic_object='$*.o'" >>$@
+	$(ECHO) "non_pic_object='$*.o'" >>$@
+	$(NASM) $(NASMFLAGS) $< -o $*.o -l $@.lst
+
+COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \
+	$(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) \
+	$(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+CCLD = $(CC)
+LINK = $(LIBTOOL) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \
+	$(AM_LDFLAGS) $(LDFLAGS) -o $@
+
+
+#$(OBJECTS): libtool
+#libtool: $(LIBTOOL_DEPS)
+#	$(SHELL) $(top_builddir)/config.status --recheck
--- a/lib-src/lame/libmp3lame/i386/Makefile.in
+++ b/lib-src/lame/libmp3lame/i386/Makefile.in
@@ -0,0 +1,633 @@
+# Makefile.in generated by automake 1.15.1 from Makefile.am.
+# @configure_input@
+
+# Copyright (C) 1994-2017 Free Software Foundation, Inc.
+
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+
+
+VPATH = @srcdir@
+am__is_gnu_make = { \
+  if test -z '$(MAKELEVEL)'; then \
+    false; \
+  elif test -n '$(MAKE_HOST)'; then \
+    true; \
+  elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \
+    true; \
+  else \
+    false; \
+  fi; \
+}
+am__make_running_with_option = \
+  case $${target_option-} in \
+      ?) ;; \
+      *) echo "am__make_running_with_option: internal error: invalid" \
+              "target option '$${target_option-}' specified" >&2; \
+         exit 1;; \
+  esac; \
+  has_opt=no; \
+  sane_makeflags=$$MAKEFLAGS; \
+  if $(am__is_gnu_make); then \
+    sane_makeflags=$$MFLAGS; \
+  else \
+    case $$MAKEFLAGS in \
+      *\\[\ \	]*) \
+        bs=\\; \
+        sane_makeflags=`printf '%s\n' "$$MAKEFLAGS" \
+          | sed "s/$$bs$$bs[$$bs $$bs	]*//g"`;; \
+    esac; \
+  fi; \
+  skip_next=no; \
+  strip_trailopt () \
+  { \
+    flg=`printf '%s\n' "$$flg" | sed "s/$$1.*$$//"`; \
+  }; \
+  for flg in $$sane_makeflags; do \
+    test $$skip_next = yes && { skip_next=no; continue; }; \
+    case $$flg in \
+      *=*|--*) continue;; \
+        -*I) strip_trailopt 'I'; skip_next=yes;; \
+      -*I?*) strip_trailopt 'I';; \
+        -*O) strip_trailopt 'O'; skip_next=yes;; \
+      -*O?*) strip_trailopt 'O';; \
+        -*l) strip_trailopt 'l'; skip_next=yes;; \
+      -*l?*) strip_trailopt 'l';; \
+      -[dEDm]) skip_next=yes;; \
+      -[JT]) skip_next=yes;; \
+    esac; \
+    case $$flg in \
+      *$$target_option*) has_opt=yes; break;; \
+    esac; \
+  done; \
+  test $$has_opt = yes
+am__make_dryrun = (target_option=n; $(am__make_running_with_option))
+am__make_keepgoing = (target_option=k; $(am__make_running_with_option))
+pkgdatadir = $(datadir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkglibexecdir = $(libexecdir)/@PACKAGE@
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+build_triplet = @build@
+host_triplet = @host@
+subdir = libmp3lame/i386
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+am__aclocal_m4_deps = $(top_srcdir)/acinclude.m4 \
+	$(top_srcdir)/configure.in
+am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
+	$(ACLOCAL_M4)
+DIST_COMMON = $(srcdir)/Makefile.am $(noinst_HEADERS) \
+	$(am__DIST_COMMON)
+mkinstalldirs = $(install_sh) -d
+CONFIG_HEADER = $(top_builddir)/config.h
+CONFIG_CLEAN_FILES =
+CONFIG_CLEAN_VPATH_FILES =
+LTLIBRARIES = $(noinst_LTLIBRARIES)
+liblameasmroutines_la_LIBADD =
+am__liblameasmroutines_la_SOURCES_DIST = choose_table.nas cpu_feat.nas \
+	fft3dn.nas fftsse.nas
+am__objects_1 = choose_table.lo cpu_feat.lo fft3dn.lo fftsse.lo
+liblameasmroutines_la_OBJECTS = $(am_liblameasmroutines_la_OBJECTS)
+AM_V_lt = $(am__v_lt_@AM_V@)
+am__v_lt_ = $(am__v_lt_@AM_DEFAULT_V@)
+am__v_lt_0 = --silent
+am__v_lt_1 = 
+@HAVE_NASM_TRUE@am_liblameasmroutines_la_rpath =
+AM_V_P = $(am__v_P_@AM_V@)
+am__v_P_ = $(am__v_P_@AM_DEFAULT_V@)
+am__v_P_0 = false
+am__v_P_1 = :
+AM_V_GEN = $(am__v_GEN_@AM_V@)
+am__v_GEN_ = $(am__v_GEN_@AM_DEFAULT_V@)
+am__v_GEN_0 = @echo "  GEN     " $@;
+am__v_GEN_1 = 
+AM_V_at = $(am__v_at_@AM_V@)
+am__v_at_ = $(am__v_at_@AM_DEFAULT_V@)
+am__v_at_0 = @
+am__v_at_1 = 
+DEFAULT_INCLUDES = -I.@am__isrc@ -I$(top_builddir)
+SOURCES = $(liblameasmroutines_la_SOURCES) \
+	$(EXTRA_liblameasmroutines_la_SOURCES)
+DIST_SOURCES = $(am__liblameasmroutines_la_SOURCES_DIST) \
+	$(EXTRA_liblameasmroutines_la_SOURCES)
+am__can_run_installinfo = \
+  case $$AM_UPDATE_INFO_DIR in \
+    n|no|NO) false;; \
+    *) (install-info --version) >/dev/null 2>&1;; \
+  esac
+HEADERS = $(noinst_HEADERS)
+am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP)
+# Read a list of newline-separated strings from the standard input,
+# and print each of them once, without duplicates.  Input order is
+# *not* preserved.
+am__uniquify_input = $(AWK) '\
+  BEGIN { nonempty = 0; } \
+  { items[$$0] = 1; nonempty = 1; } \
+  END { if (nonempty) { for (i in items) print i; }; } \
+'
+# Make sure the list of sources is unique.  This is necessary because,
+# e.g., the same source file might be shared among _SOURCES variables
+# for different programs/libraries.
+am__define_uniq_tagged_files = \
+  list='$(am__tagged_files)'; \
+  unique=`for i in $$list; do \
+    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+  done | $(am__uniquify_input)`
+ETAGS = etags
+CTAGS = ctags
+am__DIST_COMMON = $(srcdir)/Makefile.in
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+ACLOCAL = @ACLOCAL@
+ALLOCA = @ALLOCA@
+AMTAR = @AMTAR@
+AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@
+AR = @AR@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CFLAGS = @CFLAGS@
+CONFIG_DEFS = @CONFIG_DEFS@
+CONFIG_MATH_LIB = @CONFIG_MATH_LIB@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CPUCCODE = @CPUCCODE@
+CPUTYPE = @CPUTYPE@
+CYGPATH_W = @CYGPATH_W@
+DEFS = @DEFS@ @CONFIG_DEFS@
+DEPDIR = @DEPDIR@
+DLLTOOL = @DLLTOOL@
+DSYMUTIL = @DSYMUTIL@
+DUMPBIN = @DUMPBIN@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+FGREP = @FGREP@
+FRONTEND_CFLAGS = @FRONTEND_CFLAGS@
+FRONTEND_LDADD = @FRONTEND_LDADD@
+FRONTEND_LDFLAGS = @FRONTEND_LDFLAGS@
+GREP = @GREP@
+GTK_CFLAGS = @GTK_CFLAGS@
+GTK_CONFIG = @GTK_CONFIG@
+GTK_LIBS = @GTK_LIBS@
+INCLUDES = @INCLUDES@ -I$(top_srcdir)/libmp3lame/@CPUTYPE@
+INSTALL = @INSTALL@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LD = @LD@
+LDADD = @LDADD@
+LDFLAGS = @LDFLAGS@
+LIBICONV = @LIBICONV@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LIBTOOL = @LIBTOOL@
+LIBTOOL_DEPS = @LIBTOOL_DEPS@
+LIB_MAJOR_VERSION = @LIB_MAJOR_VERSION@
+LIB_MINOR_VERSION = @LIB_MINOR_VERSION@
+LIPO = @LIPO@
+LN_S = @LN_S@
+LTLIBICONV = @LTLIBICONV@
+LTLIBOBJS = @LTLIBOBJS@
+LT_SYS_LIBRARY_PATH = @LT_SYS_LIBRARY_PATH@
+MAINT = @MAINT@
+MAKEDEP = @MAKEDEP@
+MAKEINFO = @MAKEINFO@
+MANIFEST_TOOL = @MANIFEST_TOOL@
+MKDIR_P = @MKDIR_P@
+NASM = @NASM@
+NASM_FORMAT = @NASM_FORMAT@
+NM = @NM@
+NMEDIT = @NMEDIT@
+OBJDUMP = @OBJDUMP@
+OBJEXT = @OBJEXT@
+OTOOL = @OTOOL@
+OTOOL64 = @OTOOL64@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_URL = @PACKAGE_URL@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+PKG_CONFIG = @PKG_CONFIG@
+PKG_CONFIG_LIBDIR = @PKG_CONFIG_LIBDIR@
+PKG_CONFIG_PATH = @PKG_CONFIG_PATH@
+RANLIB = @RANLIB@
+RM_F = @RM_F@
+SED = @SED@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+SNDFILE_CFLAGS = @SNDFILE_CFLAGS@
+SNDFILE_LIBS = @SNDFILE_LIBS@
+STRIP = @STRIP@
+VERSION = @VERSION@
+WITH_FRONTEND = @WITH_FRONTEND@
+WITH_MP3RTP = @WITH_MP3RTP@
+WITH_MP3X = @WITH_MP3X@
+abs_builddir = @abs_builddir@
+abs_srcdir = @abs_srcdir@
+abs_top_builddir = @abs_top_builddir@
+abs_top_srcdir = @abs_top_srcdir@
+ac_ct_AR = @ac_ct_AR@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_DUMPBIN = @ac_ct_DUMPBIN@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+am__tar = @am__tar@
+am__untar = @am__untar@
+bindir = @bindir@
+build = @build@
+build_alias = @build_alias@
+build_cpu = @build_cpu@
+build_os = @build_os@
+build_vendor = @build_vendor@
+builddir = @builddir@
+datadir = @datadir@
+datarootdir = @datarootdir@
+docdir = @docdir@
+dvidir = @dvidir@
+exec_prefix = @exec_prefix@
+host = @host@
+host_alias = @host_alias@
+host_cpu = @host_cpu@
+host_os = @host_os@
+host_vendor = @host_vendor@
+htmldir = @htmldir@
+includedir = @includedir@
+infodir = @infodir@
+install_sh = @install_sh@
+libdir = @libdir@
+libexecdir = @libexecdir@
+localedir = @localedir@
+localstatedir = @localstatedir@
+mandir = @mandir@
+mkdir_p = @mkdir_p@
+oldincludedir = @oldincludedir@
+pdfdir = @pdfdir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+psdir = @psdir@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+srcdir = @srcdir@
+sysconfdir = @sysconfdir@
+target_alias = @target_alias@
+top_build_prefix = @top_build_prefix@
+top_builddir = @top_builddir@
+top_srcdir = @top_srcdir@
+AUTOMAKE_OPTIONS = foreign
+nasm_sources = \
+	choose_table.nas \
+	cpu_feat.nas \
+	fft3dn.nas \
+	fftsse.nas
+
+@HAVE_NASM_TRUE@noinst_LTLIBRARIES = liblameasmroutines.la
+@HAVE_NASM_TRUE@liblameasmroutines_la_SOURCES = $(nasm_sources)
+@HAVE_NASM_TRUE@liblameasmroutines_la_DEPENDENCIES = $(nasm_sources:.nas.lo)
+@HAVE_NASM_TRUE@am_liblameasmroutines_la_OBJECTS = \
+@HAVE_NASM_TRUE@	choose_table$U.lo \
+@HAVE_NASM_TRUE@	cpu_feat$U.lo \
+@HAVE_NASM_TRUE@	fft3dn$U.lo \
+@HAVE_NASM_TRUE@	fftsse$U.lo
+
+noinst_HEADERS = nasm.h
+SUFFIXES = .nas .lo
+EXTRA_liblameasmroutines_la_SOURCES = $(nasm_sources)
+CLEANFILES = \
+	choose_table.o.lst \
+	choose_table.lo.lst \
+	cpu_feat.o.lst \
+	cpu_feat.lo.lst \
+	fft3dn.o.lst \
+	fft3dn.lo.lst \
+	fftsse.o.lst \
+	fftsse.lo.lst
+
+EXTRA_DIST = \
+	fft.nas \
+	fftfpu.nas \
+	ffttbl.nas \
+	scalar.nas
+
+NASMFLAGS = @NASM_FORMAT@ -i $(top_srcdir)/libmp3lame/@CPUTYPE@/
+COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \
+	$(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+
+LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) \
+	$(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+
+CCLD = $(CC)
+LINK = $(LIBTOOL) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \
+	$(AM_LDFLAGS) $(LDFLAGS) -o $@
+
+all: all-am
+
+.SUFFIXES:
+.SUFFIXES: .nas .lo .o
+$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.am  $(am__configure_deps)
+	@for dep in $?; do \
+	  case '$(am__configure_deps)' in \
+	    *$$dep*) \
+	      ( cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh ) \
+	        && { if test -f $@; then exit 0; else break; fi; }; \
+	      exit 1;; \
+	  esac; \
+	done; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --foreign libmp3lame/i386/Makefile'; \
+	$(am__cd) $(top_srcdir) && \
+	  $(AUTOMAKE) --foreign libmp3lame/i386/Makefile
+Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
+	@case '$?' in \
+	  *config.status*) \
+	    cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
+	  *) \
+	    echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
+	    cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
+	esac;
+
+$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+
+$(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps)
+	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
+$(am__aclocal_m4_deps):
+
+clean-noinstLTLIBRARIES:
+	-test -z "$(noinst_LTLIBRARIES)" || rm -f $(noinst_LTLIBRARIES)
+	@list='$(noinst_LTLIBRARIES)'; \
+	locs=`for p in $$list; do echo $$p; done | \
+	      sed 's|^[^/]*$$|.|; s|/[^/]*$$||; s|$$|/so_locations|' | \
+	      sort -u`; \
+	test -z "$$locs" || { \
+	  echo rm -f $${locs}; \
+	  rm -f $${locs}; \
+	}
+
+liblameasmroutines.la: $(liblameasmroutines_la_OBJECTS) $(liblameasmroutines_la_DEPENDENCIES) $(EXTRA_liblameasmroutines_la_DEPENDENCIES) 
+	$(AM_V_CCLD)$(LINK) $(am_liblameasmroutines_la_rpath) $(liblameasmroutines_la_OBJECTS) $(liblameasmroutines_la_LIBADD) $(LIBS)
+
+mostlyclean-compile:
+	-rm -f *.$(OBJEXT)
+
+distclean-compile:
+	-rm -f *.tab.c
+
+mostlyclean-libtool:
+	-rm -f *.lo
+
+clean-libtool:
+	-rm -rf .libs _libs
+
+ID: $(am__tagged_files)
+	$(am__define_uniq_tagged_files); mkid -fID $$unique
+tags: tags-am
+TAGS: tags
+
+tags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files)
+	set x; \
+	here=`pwd`; \
+	$(am__define_uniq_tagged_files); \
+	shift; \
+	if test -z "$(ETAGS_ARGS)$$*$$unique"; then :; else \
+	  test -n "$$unique" || unique=$$empty_fix; \
+	  if test $$# -gt 0; then \
+	    $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	      "$$@" $$unique; \
+	  else \
+	    $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	      $$unique; \
+	  fi; \
+	fi
+ctags: ctags-am
+
+CTAGS: ctags
+ctags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files)
+	$(am__define_uniq_tagged_files); \
+	test -z "$(CTAGS_ARGS)$$unique" \
+	  || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \
+	     $$unique
+
+GTAGS:
+	here=`$(am__cd) $(top_builddir) && pwd` \
+	  && $(am__cd) $(top_srcdir) \
+	  && gtags -i $(GTAGS_ARGS) "$$here"
+cscopelist: cscopelist-am
+
+cscopelist-am: $(am__tagged_files)
+	list='$(am__tagged_files)'; \
+	case "$(srcdir)" in \
+	  [\\/]* | ?:[\\/]*) sdir="$(srcdir)" ;; \
+	  *) sdir=$(subdir)/$(srcdir) ;; \
+	esac; \
+	for i in $$list; do \
+	  if test -f "$$i"; then \
+	    echo "$(subdir)/$$i"; \
+	  else \
+	    echo "$$sdir/$$i"; \
+	  fi; \
+	done >> $(top_builddir)/cscope.files
+
+distclean-tags:
+	-rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags
+
+distdir: $(DISTFILES)
+	@srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \
+	list='$(DISTFILES)'; \
+	  dist_files=`for file in $$list; do echo $$file; done | \
+	  sed -e "s|^$$srcdirstrip/||;t" \
+	      -e "s|^$$topsrcdirstrip/|$(top_builddir)/|;t"`; \
+	case $$dist_files in \
+	  */*) $(MKDIR_P) `echo "$$dist_files" | \
+			   sed '/\//!d;s|^|$(distdir)/|;s,/[^/]*$$,,' | \
+			   sort -u` ;; \
+	esac; \
+	for file in $$dist_files; do \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  if test -d $$d/$$file; then \
+	    dir=`echo "/$$file" | sed -e 's,/[^/]*$$,,'`; \
+	    if test -d "$(distdir)/$$file"; then \
+	      find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \
+	    fi; \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -fpR $(srcdir)/$$file "$(distdir)$$dir" || exit 1; \
+	      find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \
+	    fi; \
+	    cp -fpR $$d/$$file "$(distdir)$$dir" || exit 1; \
+	  else \
+	    test -f "$(distdir)/$$file" \
+	    || cp -p $$d/$$file "$(distdir)/$$file" \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(LTLIBRARIES) $(HEADERS)
+installdirs:
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	if test -z '$(STRIP)'; then \
+	  $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	    install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	      install; \
+	else \
+	  $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	    install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	    "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \
+	fi
+mostlyclean-generic:
+
+clean-generic:
+	-test -z "$(CLEANFILES)" || rm -f $(CLEANFILES)
+
+distclean-generic:
+	-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
+	-test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic clean-libtool clean-noinstLTLIBRARIES \
+	mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-compile distclean-generic \
+	distclean-tags
+
+dvi: dvi-am
+
+dvi-am:
+
+html: html-am
+
+html-am:
+
+info: info-am
+
+info-am:
+
+install-data-am:
+
+install-dvi: install-dvi-am
+
+install-dvi-am:
+
+install-exec-am:
+
+install-html: install-html-am
+
+install-html-am:
+
+install-info: install-info-am
+
+install-info-am:
+
+install-man:
+
+install-pdf: install-pdf-am
+
+install-pdf-am:
+
+install-ps: install-ps-am
+
+install-ps-am:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-compile mostlyclean-generic \
+	mostlyclean-libtool
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am:
+
+.MAKE: install-am install-strip
+
+.PHONY: CTAGS GTAGS TAGS all all-am check check-am clean clean-generic \
+	clean-libtool clean-noinstLTLIBRARIES cscopelist-am ctags \
+	ctags-am distclean distclean-compile distclean-generic \
+	distclean-libtool distclean-tags distdir dvi dvi-am html \
+	html-am info info-am install install-am install-data \
+	install-data-am install-dvi install-dvi-am install-exec \
+	install-exec-am install-html install-html-am install-info \
+	install-info-am install-man install-pdf install-pdf-am \
+	install-ps install-ps-am install-strip installcheck \
+	installcheck-am installdirs maintainer-clean \
+	maintainer-clean-generic mostlyclean mostlyclean-compile \
+	mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \
+	tags tags-am uninstall uninstall-am
+
+.PRECIOUS: Makefile
+
+
+ECHO ?= echo
+
+.nas.o: $< nasm.h
+	$(NASM) $(NASMFLAGS) $< -o $@ -l $@.lst
+
+.nas.lo: $< nasm.h
+	$(ECHO) '# Generated by ltmain.sh - GNU libtool 1.5.22 (1.1220.2.365 2005/12/18 22:14:06)' >$@
+	$(ECHO) "pic_object='$*.o'" >>$@
+	$(ECHO) "non_pic_object='$*.o'" >>$@
+	$(NASM) $(NASMFLAGS) $< -o $*.o -l $@.lst
+
+#$(OBJECTS): libtool
+#libtool: $(LIBTOOL_DEPS)
+#	$(SHELL) $(top_builddir)/config.status --recheck
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:
--- a/lib-src/lame/libmp3lame/i386/choose_table.nas
+++ b/lib-src/lame/libmp3lame/i386/choose_table.nas
@@ -0,0 +1,447 @@
+; new count bit routine
+;	part of this code is origined from
+;	new GOGO-no-coda (1999, 2000)
+;	Copyright (C) 1999 shigeo
+;	modified by Keiichi SAKAI
+
+%include "nasm.h"
+
+	globaldef	choose_table_MMX
+	globaldef	MMX_masking
+
+	externdef	largetbl
+	externdef	t1l
+	externdef	table23
+	externdef	table56
+
+	segment_data
+	align	16
+D14_14_14_14	dd	0x000E000E, 0x000E000E
+D15_15_15_15	dd	0xfff0fff0, 0xfff0fff0
+mul_add		dd	0x00010010, 0x00010010
+mul_add23	dd	0x00010003, 0x00010003
+mul_add56	dd	0x00010004, 0x00010004
+tableDEF
+	dd	0x00010003,0x01,0x00050005,0x05,0x00070006,0x07,0x00090008,0x08,0x000a0008, 0x09
+	dd	0x000a0009,0x0a,0x000b000a,0x0a,0x000b000a,0x0b,0x000c000a,0x0a,0x000c000b, 0x0b
+	dd	0x000c000b,0x0c,0x000d000c,0x0c,0x000d000c,0x0d,0x000d000c,0x0d,0x000e000d, 0x0e
+	dd	0x000b000e,0x0e,0x00040005,0x04,0x00060005,0x06,0x00080007,0x08,0x00090008, 0x09
+	dd	0x000a0009,0x0a,0x000b0009,0x0a,0x000b000a,0x0b,0x000b000a,0x0b,0x000c000a, 0x0b
+	dd	0x000c000b,0x0b,0x000c000b,0x0c,0x000d000c,0x0c,0x000e000c,0x0d,0x000d000c, 0x0e
+	dd	0x000e000d,0x0e,0x000b000d,0x0e,0x00070006,0x07,0x00080007,0x08,0x00090007, 0x09
+	dd	0x000a0008,0x0a,0x000b0009,0x0b,0x000b0009,0x0b,0x000c000a,0x0c,0x000c000a, 0x0c
+	dd	0x000d000a,0x0b,0x000c000b,0x0c,0x000d000b,0x0c,0x000d000c,0x0d,0x000d000c, 0x0d
+	dd	0x000e000d,0x0e,0x000e000d,0x0f,0x000c000d,0x0f,0x00090007,0x08,0x00090008, 0x09
+	dd	0x000a0008,0x0a,0x000b0009,0x0b,0x000b0009,0x0b,0x000c000a,0x0c,0x000c000a, 0x0c
+	dd	0x000c000b,0x0c,0x000d000b,0x0c,0x000d000b,0x0d,0x000e000c,0x0d,0x000e000c, 0x0d
+	dd	0x000e000c,0x0d,0x000f000d,0x0e,0x000f000d,0x0f,0x000d000d,0x0f,0x000a0008, 0x09
+	dd	0x000a0008,0x09,0x000b0009,0x0b,0x000b0009,0x0b,0x000c000a,0x0c,0x000c000a, 0x0c
+	dd	0x000d000b,0x0d,0x000d000b,0x0d,0x000d000b,0x0c,0x000e000b,0x0d,0x000e000c, 0x0d
+	dd	0x000e000c,0x0e,0x000f000c,0x0e,0x000f000d,0x0f,0x000f000d,0x0f,0x000c000d, 0x10
+	dd	0x000a0009,0x0a,0x000a0009,0x0a,0x000b0009,0x0b,0x000b000a,0x0c,0x000c000a, 0x0c
+	dd	0x000d000a,0x0c,0x000d000b,0x0d,0x000e000b,0x0d,0x000d000b,0x0d,0x000e000b, 0x0d
+	dd	0x000e000c,0x0e,0x000f000c,0x0d,0x000f000d,0x0f,0x000f000d,0x0f,0x0010000d, 0x10
+	dd	0x000d000e,0x10,0x000b000a,0x0a,0x000b0009,0x0b,0x000b000a,0x0c,0x000c000a, 0x0c
+	dd	0x000d000a,0x0d,0x000d000b,0x0d,0x000d000b,0x0d,0x000d000b,0x0d,0x000e000b, 0x0d
+	dd	0x000e000c,0x0e,0x000e000c,0x0e,0x000e000c,0x0e,0x000f000d,0x0f,0x000f000d, 0x0f
+	dd	0x0010000e,0x10,0x000d000e,0x10,0x000b000a,0x0b,0x000b000a,0x0b,0x000c000a, 0x0c
+	dd	0x000c000b,0x0d,0x000d000b,0x0d,0x000d000b,0x0d,0x000d000b,0x0e,0x000e000c, 0x0e
+	dd	0x000e000c,0x0e,0x000f000c,0x0e,0x000f000c,0x0f,0x000f000c,0x0f,0x000f000d, 0x0f
+	dd	0x0011000d,0x10,0x0011000d,0x12,0x000d000e,0x12,0x000b000a,0x0a,0x000c000a, 0x0a
+	dd	0x000c000a,0x0b,0x000d000b,0x0c,0x000d000b,0x0c,0x000d000b,0x0d,0x000e000b, 0x0d
+	dd	0x000e000c,0x0e,0x000f000c,0x0e,0x000f000c,0x0e,0x000f000c,0x0e,0x000f000d, 0x0f
+	dd	0x0010000d,0x0f,0x0010000e,0x10,0x0010000e,0x11,0x000d000e,0x11,0x000c000a, 0x0b
+	dd	0x000c000a,0x0b,0x000c000b,0x0c,0x000d000b,0x0c,0x000d000b,0x0d,0x000e000b, 0x0d
+	dd	0x000e000c,0x0d,0x000f000c,0x0f,0x000f000c,0x0e,0x000f000d,0x0f,0x000f000d, 0x0f
+	dd	0x0010000d,0x10,0x000f000d,0x10,0x0010000e,0x10,0x000f000e,0x12,0x000e000e, 0x11
+	dd	0x000c000b,0x0b,0x000d000b,0x0c,0x000c000b,0x0c,0x000d000b,0x0d,0x000e000c, 0x0d
+	dd	0x000e000c,0x0e,0x000e000c,0x0e,0x000e000c,0x0f,0x000f000c,0x0e,0x0010000d, 0x0f
+	dd	0x0010000d,0x10,0x0010000d,0x0f,0x0011000d,0x10,0x0011000e,0x11,0x0010000f, 0x12
+	dd	0x000d000e,0x13,0x000d000b,0x0c,0x000d000b,0x0c,0x000d000b,0x0c,0x000d000b, 0x0d
+	dd	0x000e000c,0x0e,0x000e000c,0x0e,0x000f000c,0x0e,0x0010000c,0x0e,0x0010000d, 0x0f
+	dd	0x0010000d,0x0f,0x0010000d,0x0f,0x0010000d,0x10,0x0010000e,0x11,0x000f000e, 0x11
+	dd	0x0010000e,0x11,0x000e000f,0x12,0x000d000c,0x0c,0x000e000c,0x0d,0x000e000b, 0x0d
+	dd	0x000e000c,0x0e,0x000e000c,0x0e,0x000f000c,0x0f,0x000f000d,0x0e,0x000f000d, 0x0f
+	dd	0x000f000d,0x10,0x0011000d,0x10,0x0010000d,0x11,0x0010000d,0x11,0x0010000e, 0x11
+	dd	0x0010000e,0x12,0x0012000f,0x12,0x000e000f,0x12,0x000f000c,0x0d,0x000e000c, 0x0d
+	dd	0x000e000c,0x0e,0x000e000c,0x0f,0x000f000c,0x0f,0x000f000d,0x0f,0x0010000d, 0x10
+	dd	0x0010000d,0x10,0x0010000d,0x10,0x0012000e,0x10,0x0011000e,0x10,0x0011000e, 0x11
+	dd	0x0011000e,0x12,0x0013000e,0x11,0x0011000f,0x12,0x000e000f,0x12,0x000e000d, 0x0e
+	dd	0x000f000d,0x0e,0x000d000d,0x0e,0x000e000d,0x0f,0x0010000d,0x0f,0x0010000d, 0x0f
+	dd	0x000f000d,0x11,0x0010000d,0x10,0x0010000e,0x10,0x0011000e,0x13,0x0012000e, 0x11
+	dd	0x0011000e,0x11,0x0013000f,0x11,0x0011000f,0x13,0x0010000e,0x12,0x000e000f, 0x12
+	dd	0x000b000d,0x0d,0x000b000d,0x0e,0x000b000d,0x0f,0x000c000d,0x10,0x000c000d, 0x10
+	dd	0x000d000d,0x10,0x000d000d,0x11,0x000d000e,0x10,0x000e000e,0x11,0x000e000e, 0x11
+	dd	0x000e000e,0x12,0x000e000e,0x12,0x000e000f,0x15,0x000e000f,0x14,0x000e000f, 0x15
+	dd	0x000c000f,0x12
+
+tableABC
+	dd	0x00020004,0x1,0x00040004,0x4,0x00060006,0x7,0x00080008,0x9,0x00090009,0xa,0x000a000a,0xa
+	dd	0x0009000a,0xa,0x000a000a,0xb,0x00000000,0x0,0x00020003,0x1,0x00040004,0x4,0x00070006,0x7
+	dd	0x00090007,0x9,0x00090009,0x9,0x000a000a,0xa,0x00000000,0x0,0x00040004,0x4,0x00050005,0x6
+	dd	0x00060006,0x8,0x00080007,0x9,0x000a0009,0xa,0x000a0009,0xb,0x0009000a,0xa,0x000a000a,0xa
+	dd	0x00000000,0x0,0x00040004,0x4,0x00040005,0x6,0x00060006,0x8,0x000a0007,0x9,0x000a0008,0x9
+	dd	0x000a000a,0xa,0x00000000,0x0,0x00060006,0x7,0x00070006,0x8,0x00080007,0x9,0x00090008,0xa
+	dd	0x000a0009,0xb,0x000b000a,0xc,0x000a0009,0xb,0x000a000a,0xb,0x00000000,0x0,0x00070005,0x7
+	dd	0x00060006,0x7,0x00080007,0x9,0x000a0008,0xa,0x000a0009,0xa,0x000b000a,0xb,0x00000000,0x0
+	dd	0x00080007,0x8,0x00080007,0x9,0x00090008,0xa,0x000b0008,0xb,0x000a0009,0xc,0x000c000a,0xc
+	dd	0x000a000a,0xb,0x000b000a,0xc,0x00000000,0x0,0x00090007,0x8,0x000a0007,0x9,0x000a0008,0xa
+	dd	0x000b0009,0xb,0x000b0009,0xb,0x000c000a,0xb,0x00000000,0x0,0x00090008,0x9,0x000a0008,0xa
+	dd	0x000a0009,0xb,0x000b0009,0xc,0x000b000a,0xc,0x000c000a,0xc,0x000b000a,0xc,0x000c000b,0xc
+	dd	0x00000000,0x0,0x00090008,0x8,0x00090008,0x9,0x000a0009,0xa,0x000b0009,0xb,0x000c000a,0xb
+	dd	0x000c000b,0xc,0x00000000,0x0,0x00090009,0xa,0x000a0009,0xb,0x000b000a,0xc,0x000c000a,0xc
+	dd	0x000c000a,0xd,0x000d000b,0xd,0x000c000a,0xc,0x000d000b,0xd,0x00000000,0x0,0x000a0009,0x9
+	dd	0x000a0009,0xa,0x000b000a,0xb,0x000b000a,0xc,0x000d000b,0xc,0x000d000b,0xc,0x00000000,0x0
+	dd	0x00090009,0x9,0x00090009,0xa,0x00090009,0xb,0x000a000a,0xc,0x000b000a,0xc,0x000c000b,0xc
+	dd	0x000c000b,0xd,0x000c000c,0xd,0x00000000,0x0,0x00000000,0x0,0x00000000,0x0,0x00000000,0x0
+	dd	0x00000000,0x0,0x00000000,0x0,0x00000000,0x0,0x00000000,0x0,0x0009000a,0xa,0x0009000a,0xa
+	dd	0x000a000a,0xb,0x000b000b,0xc,0x000c000b,0xc,0x000c000b,0xd,0x000c000b,0xd,0x000c000c,0xd
+	dd	0x00000000,0x0,0x00000000,0x0,0x00000000,0x0,0x00000000,0x0,0x00000000,0x0,0x00000000,0x0
+	dd	0x0,0x00000000, 0x0,0x00000000
+
+linbits32
+	dd	0x00040004,0x10001,0x00040004,0x20002,0x00040004,0x30003,0x00040004,0x40004
+	dd	0x00050005,0x60006,0x00060006,0x60006,0x00070007,0x80008,0x00080008,0x80008
+	dd	0x00090009,0xa000a,0x000b000b,0xa000a,0x000b000b,0xd000d,0x000d000d,0xd000d
+	dd	0x000d000d,0xd000d
+
+
+choose_table_H
+	dw	0x1810, 0x1811, 0x1812, 0x1813, 0x1914, 0x1a14, 0x1b15, 0x1c15
+	dw	0x1d16, 0x1e16, 0x1e17, 0x1f17, 0x1f17
+
+choose_jump_table_L:
+	dd	table_MMX.L_case_0    - choose_table_MMX
+	dd	table_MMX.L_case_1    - choose_table_MMX
+	dd	table_MMX.L_case_2    - choose_table_MMX
+	dd	table_MMX.L_case_3    - choose_table_MMX
+	dd	table_MMX.L_case_45   - choose_table_MMX
+	dd	table_MMX.L_case_45   - choose_table_MMX
+	dd	table_MMX.L_case_67   - choose_table_MMX
+	dd	table_MMX.L_case_67   - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+	dd	table_MMX.L_case_8_15 - choose_table_MMX
+
+	segment_code
+;
+; use MMX
+;
+
+PIC_OFFSETTABLE
+
+	align	16
+; int choose_table(int *ix, int *end, int *s)
+choose_table_MMX:
+	push	ebp
+	call	get_pc.bp
+	add	ebp, PIC_BASE()
+
+	mov	ecx,[esp+8]	;ecx = begin
+	mov	edx,[esp+12]	;edx = end
+	sub	ecx,edx		;ecx = begin-end(should be minus)
+	test	ecx,8
+ 	pxor	mm0,mm0		;mm0=[0:0]
+	movq	mm1,[edx+ecx]
+	jz	.lp
+
+	add	ecx,8
+	jz	.exit
+
+	align	4
+.lp:
+	movq	mm4,[edx+ecx]
+	movq	mm5,[edx+ecx+8]
+	add	ecx,16
+	psubusw	mm4,mm0	; $BK\Ev$O(B dword $B$G$J$$$H$$$1$J$$$N$@$,(B
+	psubusw	mm5,mm1	; $B$=$s$J%3%^%s%I$O$J$$(B :-p
+	paddw	mm0,mm4 ; $B$,(B, $B$3$3$G07$&CM$NHO0O$O(B 8191+15 $B0J2<$J$N$GLdBj$J$$(B
+	paddw	mm1,mm5
+	jnz	.lp
+.exit:
+	psubusw	mm1,mm0	; $B$3$l$bK\Ev$O(B dword $B$G$J$$$H$$$1$J$$(B
+	paddw	mm0,mm1
+
+	movq	mm4,mm0
+	punpckhdq	mm4,mm4
+	psubusw	mm4,mm0	; $B$3$l$bK\Ev$O(B dword $B$G$J$$$H$$$1$J$$(B
+	paddw	mm0,mm4
+	movd	eax,mm0
+
+	cmp	eax,15
+	ja	.with_ESC
+	lea	ecx,[PIC_EBP_REL(choose_table_MMX)]
+	add	ecx,[PIC_EBP_REL(choose_jump_table_L+eax*4)]
+	jmp 	ecx
+
+.with_ESC1:
+	emms
+	mov	ecx, [esp+16]	; *s
+	mov	[ecx], eax
+	or	eax,-1
+	pop	ebp
+	ret
+
+.with_ESC:
+	cmp	eax, 8191+15
+	ja	.with_ESC1
+
+	sub	eax,15
+	push	ebx
+	push	esi
+	bsr	eax, eax
+%assign _P 4*2
+	movq    mm5, [PIC_EBP_REL(D15_15_15_15)]
+	movq	mm6, [PIC_EBP_REL(D14_14_14_14)]
+	movq	mm3, [PIC_EBP_REL(mul_add)]
+
+	mov	ecx, [esp+_P+8]		; = ix
+;	mov	edx, [esp+_P+12]	; = end
+	sub	ecx, edx
+
+	xor	esi, esi	; sum = 0
+	test    ecx, 8
+	pxor	mm7, mm7	; linbits_sum, 14$B$r1[$($?$b$N$N?t(B
+	jz	.H_dual_lp1
+
+	movq	mm0, [edx+ecx]
+	add	ecx,8
+	packssdw	mm0,mm7
+	movq	mm2, mm0
+	paddusw	mm0, mm5	; mm0 = min(ix, 15)+0xfff0
+	pcmpgtw	mm2, mm6	; 14$B$h$jBg$-$$$+!)(B
+	psubw	mm7, mm2	; 14$B$h$jBg$-$$$H$-(B linbits_sum++;
+	pmaddwd	mm0, mm3	; {0, 0, y, x}*{1, 16, 1, 16}
+	movd	ebx, mm0
+	mov	esi, [PIC_EBP_REL(largetbl+ebx*4+(16*16+16)*4)]
+
+	jz	.H_dual_exit
+
+	align   4
+.H_dual_lp1:
+	movq	mm0, [edx+ecx]
+	movq	mm1, [edx+ecx+8]
+	packssdw	mm0,mm1
+	movq	mm2, mm0
+	paddusw	mm0, mm5	; mm0 = min(ix, 15)+0xfff0
+	pcmpgtw	mm2, mm6	; 14$B$h$jBg$-$$$+!)(B
+	pmaddwd	mm0, mm3	; {y, x, y, x}*{1, 16, 1, 16}
+	movd	ebx, mm0
+	punpckhdq	mm0,mm0
+	add	esi, [PIC_EBP_REL(largetbl+ebx*4+(16*16+16)*4)]
+	movd	ebx, mm0
+	add	esi, [PIC_EBP_REL(largetbl+ebx*4+(16*16+16)*4)]
+	add	ecx, 16
+	psubw	mm7, mm2	; 14$B$h$jBg$-$$$H$-(B linbits_sum++;
+	jnz	.H_dual_lp1
+
+.H_dual_exit:
+	pmov	mm1,mm7
+	punpckhdq	mm7,mm7
+	paddd	mm7,mm1
+	punpckldq	mm7,mm7
+
+	pmaddwd	mm7, [PIC_EBP_REL(linbits32+eax*8)]	; linbits
+	mov	ax, [PIC_EBP_REL(choose_table_H+eax*2)]
+
+	movd	ecx, mm7
+	punpckhdq	mm7,mm7
+	movd	edx,mm7
+	emms
+	shl	edx, 16
+	add	ecx, edx
+
+	add	ecx, esi
+
+	pop	esi
+	pop	ebx
+
+	mov	edx, ecx
+	and	ecx, 0xffff	; ecx = sum2
+	shr	edx, 16	; edx = sum
+
+	cmp	edx, ecx
+	jle	.chooseE_s1
+	mov	edx, ecx
+	shr	eax, 8
+.chooseE_s1:
+	mov	ecx, [esp+16] ; *s
+	and	eax, 0xff
+	add	[ecx], edx
+	pop	ebp
+	ret
+
+table_MMX.L_case_0:
+	emms
+	pop	ebp
+	ret
+
+table_MMX.L_case_1:
+	emms
+	mov	eax, [esp+16] ; *s
+	mov	ecx, [esp+8] ; *ix
+	sub	ecx, edx
+	push	ebx
+.lp:
+	mov	ebx, [edx+ecx]
+	add	ebx, ebx
+	add	ebx, [edx+ecx+4]
+	movzx	ebx, byte [PIC_EBP_REL(ebx+t1l)]
+	add	[eax], ebx
+	add	ecx, 8
+	jnz	.lp
+	pop	ebx
+	mov	eax, 1
+	pop	ebp
+	ret
+
+table_MMX.L_case_45:
+	push	dword 7
+	lea	ecx, [PIC_EBP_REL(tableABC+9*8)]
+	jmp	from3
+
+table_MMX.L_case_67:
+	push	dword 10
+	lea	ecx, [PIC_EBP_REL(tableABC)]
+	jmp	from3
+
+table_MMX.L_case_8_15:
+	push	dword 13
+	lea	ecx, [PIC_EBP_REL(tableDEF)]
+from3:
+	mov	eax,[esp+12]	;eax = *begin
+;	mov	edx,[esp+16]	;edx = *end
+
+	push	ebx
+	sub	eax, edx
+
+	movq	mm5,[PIC_EBP_REL(mul_add)]
+	pxor	mm2,mm2	;mm2 = sum
+
+	test	eax, 8
+	jz	.choose3_lp1
+; odd length
+	movq	mm0,[edx+eax]	;mm0 = ix[0] | ix[1]
+	add	eax,8
+	packssdw	mm0,mm2
+
+	pmaddwd	mm0,mm5
+	movd	ebx,mm0
+
+	movq	mm2,  [ecx+ebx*8]
+
+	jz	.choose3_exit
+
+	align	4
+.choose3_lp1
+	movq	mm0,[edx+eax]
+	movq	mm1,[edx+eax+8]
+	add	eax,16
+	packssdw	mm0,mm1 ;mm0 = ix[0]|ix[1]|ix[2]|ix[3]
+	pmaddwd	mm0,mm5
+	movd	ebx,mm0
+	punpckhdq	mm0,mm0
+	paddd	mm2, [ecx+ebx*8]
+	movd	ebx,mm0
+	paddd	mm2, [ecx+ebx*8]
+	jnz	.choose3_lp1
+.choose3_exit
+;	xor	eax,eax
+	movd	ebx, mm2
+	punpckhdq	mm2,mm2
+	mov	ecx, ebx
+	and	ecx, 0xffff	; ecx = sum2
+	shr	ebx, 16	; ebx = sum1
+	movd	edx, mm2	; edx = sum
+
+	cmp	edx, ebx
+	jle	.choose3_s1
+	mov	edx, ebx
+	inc	eax
+.choose3_s1:
+	emms
+	pop	ebx
+	cmp	edx, ecx
+	jle	.choose3_s2
+	mov	edx, ecx
+	mov	eax, 2
+.choose3_s2:
+	pop	ecx
+	add	eax, ecx
+	mov	ecx, [esp+16] ; *s
+	add	[ecx], edx
+	pop	ebp
+	ret
+
+table_MMX.L_case_2:
+	push	dword 2
+	lea	ecx,[PIC_EBP_REL(table23)]
+	pmov	mm5,[PIC_EBP_REL(mul_add23)]
+	jmp	from2
+table_MMX.L_case_3:
+	push	dword 5
+	lea	ecx,[PIC_EBP_REL(table56)]
+	pmov	mm5,[PIC_EBP_REL(mul_add56)]
+from2:
+	mov	eax,[esp+12]	;eax = *begin
+;	mov	edx,[esp+16]	;edx = *end
+	push	ebx
+	push	edi
+
+	sub	eax, edx
+	xor	edi, edi
+	test	eax, 8
+	jz	.choose2_lp1
+; odd length
+	movq	mm0,[edx+eax]	;mm0 = ix[0] | ix[1]
+	pxor	mm2,mm2		;mm2 = sum
+	packssdw	mm0,mm2
+
+	pmaddwd	mm0,mm5
+	movd	ebx,mm0
+
+	mov	edi,  [ecx+ebx*4]
+
+	add	eax,8
+	jz	.choose2_exit
+
+	align	4
+.choose2_lp1
+	movq	mm0,[edx+eax]
+	movq	mm1,[edx+eax+8]
+	packssdw	mm0,mm1 ;mm0 = ix[0]|ix[1]|ix[2]|ix[3]
+	pmaddwd	mm0,mm5
+	movd	ebx,mm0
+	punpckhdq	mm0,mm0
+	add	edi, [ecx+ebx*4]
+	movd	ebx, mm0
+	add	edi, [ecx+ebx*4]
+	add	eax,16
+	jnc	.choose2_lp1
+.choose2_exit
+	mov	ecx, edi
+	pop	edi
+	pop	ebx
+	pop	eax ; table num.
+	emms
+
+	mov	edx, ecx
+	and	ecx, 0xffff	; ecx = sum2
+	shr	edx, 16	; edx = sum1
+
+	cmp	edx, ecx
+	jle	.choose2_s1
+	mov	edx, ecx
+	inc	eax
+.choose2_s1:
+	mov	ecx, [esp+16] ; *s
+	add	[ecx], edx
+	pop	ebp
+	ret
+
+	end
--- a/lib-src/lame/libmp3lame/i386/cpu_feat.nas
+++ b/lib-src/lame/libmp3lame/i386/cpu_feat.nas
@@ -0,0 +1,107 @@
+;
+;
+; 	assembler routines to detect CPU-features
+;
+;	MMX / 3DNow! / SSE / SSE2
+;
+;	for the LAME project
+;	Frank Klemm, Robert Hegemann 2000-10-12
+;
+
+%include "nasm.h"
+
+	globaldef	has_MMX_nasm
+	globaldef	has_3DNow_nasm
+	globaldef	has_SSE_nasm
+	globaldef	has_SSE2_nasm
+
+        segment_code
+
+testCPUID:
+	pushfd	                        
+	pop	eax
+	mov	ecx,eax
+	xor	eax,0x200000
+	push	eax
+	popfd
+	pushfd
+	pop	eax
+	cmp	eax,ecx
+	ret
+
+;---------------------------------------
+;	int  has_MMX_nasm (void)
+;---------------------------------------
+
+has_MMX_nasm:
+        pushad
+	call	testCPUID
+	jz	return0		; no CPUID command, so no MMX
+
+	mov	eax,0x1
+	CPUID
+	test	edx,0x800000
+	jz	return0		; no MMX support
+	jmp	return1		; MMX support
+        
+;---------------------------------------
+;	int  has_SSE_nasm (void)
+;---------------------------------------
+
+has_SSE_nasm:
+        pushad
+	call	testCPUID
+	jz	return0		; no CPUID command, so no SSE
+        
+	mov	eax,0x1
+	CPUID
+	test	edx,0x02000000
+	jz	return0		; no SSE support
+	jmp	return1		; SSE support
+        
+;---------------------------------------
+;	int  has_SSE2_nasm (void)
+;---------------------------------------
+
+has_SSE2_nasm:
+        pushad
+	call	testCPUID
+	jz	return0		; no CPUID command, so no SSE2
+        
+	mov	eax,0x1
+	CPUID
+	test	edx,0x04000000
+	jz	return0		; no SSE2 support
+	jmp	return1		; SSE2 support
+        
+;---------------------------------------
+;	int  has_3DNow_nasm (void)
+;---------------------------------------
+
+has_3DNow_nasm:
+        pushad
+	call	testCPUID
+	jz	return0		; no CPUID command, so no 3DNow!
+
+	mov	eax,0x80000000
+	CPUID
+	cmp	eax,0x80000000
+	jbe	return0		; no extended MSR(1), so no 3DNow!
+
+	mov	eax,0x80000001
+	CPUID
+	test	edx,0x80000000
+	jz	return0		; no 3DNow! support
+				; 3DNow! support
+return1:
+	popad
+	xor	eax,eax
+	inc	eax
+	ret
+
+return0:
+	popad
+	xor	eax,eax
+	ret
+        
+        end
--- a/lib-src/lame/libmp3lame/i386/fft.nas
+++ b/lib-src/lame/libmp3lame/i386/fft.nas
@@ -0,0 +1,267 @@
+
+;	for new GOGO-no-coda (1999/09)
+;	Copyright (C) 1999 shigeo
+;	special thanks to Keiichi SAKAI, URURI
+%include "nasm.h"
+
+	globaldef fht_3DN
+	globaldef fht
+	externdef costab_fft
+	externdef sintab_fft
+	externdef gray_index
+
+	segment_data
+	align 16
+D_MSB1_0	dd	0         ,0x80000000
+D_SQRT2	dd	1.414213562,1.414213562
+t_s0	dd	0	;[ t_c:t_s]
+t_c0	dd	0
+t_c1	dd	0	;[-t_s:t_c]
+t_s1	dd	0
+D_s1c1	dd	0, 0
+D_Mc1s1	dd	0, 0
+D_s2c2	dd	0, 0
+D_Mc2s2	dd	0, 0
+D_0_1	dd	1.0, 0.0
+S_05	DD	0.5
+S_00005	DD	0.0005
+fht		dd	0	;<3B>ؿ<EFBFBD><D8BF>ݥ<EFBFBD><DDA5><EFBFBD><EFBFBD><EFBFBD>
+
+	segment_code
+
+;************************************************************************
+
+;	by shigeo
+;	99/08/16
+;	23000clk <20>ɤ<EFBFBD><C9A4>ä<EFBFBD><C3A4><EFBFBD>
+;	18500clk bit reversal from gogo1 by URURI
+
+;void fht(float *fz, int n);
+	align 16
+fht_3DN:
+	push	ebx
+	push	esi
+	push	edi
+	push	ebp
+%assign _P 4*4
+	;<3B>ޤ<EFBFBD><DEA4>ǽ<EFBFBD><C7BD>Υ롼<CEA5><EBA1BC>... <20><>fht()<29>γ<EFBFBD><CEB3>ذ<EFBFBD>ư
+
+	mov	esi,[esp+_P+4]	;esi=fz
+	mov	ecx,[esp+_P+8]	;ecx=n
+
+	;<3B>ᥤ<EFBFBD><E1A5A4><EFBFBD>롼<EFBFBD><EBA1BC>
+	movq	mm7,[D_MSB1_0]	;mm7=[1<<31:0]
+
+%assign LOCAL_STACK	16
+	sub	esp,LOCAL_STACK
+%assign _P (_P+LOCAL_STACK)
+	xor	eax,eax
+	mov	[esp],eax	;k=0
+%define k dword [esp]
+%define kx	dword [esp+4]
+%define fn dword [esp+8]
+
+.lp30:	;k=0; do{
+	mov	ecx,k
+	add	ecx,2
+	mov	k,ecx
+	mov	eax,1
+	shl	eax,cl		;eax=k1 = 1<<k
+	lea	ebx,[eax+eax]	;ebx=k2 = k1*2
+	lea	ecx,[eax+eax*2]	;ecx=k3 = k2 + k1 = k1*3
+	lea	edx,[ebx+ebx]	;edx=k4 = k1*4
+	mov	esi,eax
+	shr	esi,1		;esi=kx=k1>>1
+	mov	kx,esi		;<3B><>¸(<28><><EFBFBD>ǻȤ<C7BB>)
+	mov	edi,[esp+_P+4]	;edi=fi=fz
+	lea	ebp,[edi+esi*4]	;ebp=gi=fz+kx
+	mov	esi,[esp+_P+8]	;esi=n
+	lea	esi,[edi+esi*4]	;esi=fn=fz+n
+	movq	mm6,[D_SQRT2]	;mm6=[<5B><>2:<3A><>2]
+
+.lp31:	;fn=fz+n; do{ FLOAT g0,f0,f1,...
+	movd	mm0,[edi]	;mm0=[0:fi[ 0]]
+	movd	mm1,[edi+eax*4]	;mm1=[0:fi[k1]]
+	punpckldq	mm0,mm0	;mm0=[fi_0 :fi_0 ]
+	punpckldq	mm1,mm1	;mm1=[fi_k1:fi_k1]
+	movd	mm2,[edi+ebx*4]
+	movd	mm3,[edi+ecx*4]
+	punpckldq	mm2,mm2	;mm2=[fi_k2:fi_k2]
+	punpckldq	mm3,mm3	;mm3=[fi_k3:fi_k3]
+	pxor	mm1,mm7		;mm1=[-fi_k1:fi_k1]
+	pxor	mm3,mm7		;mm3=[-fi_k3:fi_k3]
+	pfadd	mm0,mm1		;mm0=[f1:f0]=[fi_0 -fi_k1 : fi_0 +fi_k1]
+	pfadd	mm2,mm3		;mm2=[f3:f2]=[fi_k2-fi_k3 : fi_k2+fi_k3]
+	movq	mm3,mm0		;mm3=[f1:f0]
+	pfadd	mm0,mm2		;mm0=[f1+f3:f0+f2]
+	movd	[edi],mm0	;fi[0]=f0+f2
+	psrlq	mm0,32		;mm0=[0:f1+f3]
+	pfsub	mm3,mm2		;mm3=[f1-f3:f0-f2]
+	movd	[edi+eax*4],mm0	;fi[k1]=f1+f3
+	movd	[edi+ebx*4],mm3	;fi[k2]=f0-f2
+	psrlq	mm3,32		;mm3=[0:f1-f3]
+	movd	[edi+ecx*4],mm3	;fi[k3]=f1-f3
+
+	movd	mm0,[ebp]	;mm0=[0:gi_0]
+	movd	mm1,[ebp+eax*4]	;mm1=[0:gi_k1]
+	punpckldq	mm0,mm0	;mm0=[gi_0 :gi_0 ]
+	punpckldq	mm1,mm1	;mm1=[gi_k1:gi_k1]
+	movd	mm2,[ebp+ebx*4]	;mm2=[0:gi_k2]
+	pxor	mm1,mm7		;mm1=[-gi_k1:gi_k1]
+	punpckldq	mm2,[ebp+ecx*4]	;mm2=[gi_k3:gi_k2]
+	pfadd	mm0,mm1		;mm0=[g1:g0]=[gi_0 -gi_k1:gi_0 +gi_k1]
+	pfmul	mm2,mm6		;mm2=[g3:g2]=sqrt2 * [gi_k3:gi_k2]
+	movq	mm1,mm0		;mm1=[g1:g0]
+	pfadd	mm0,mm2		;mm0=[g1+g3:g0+g2]
+	movd	[ebp],mm0	;gi[0]=g0+g2
+	psrlq	mm0,32		;mm0=[0:g1+g3]
+	pfsub	mm1,mm2		;mm1=[g1-g3:g0-g2]
+	movd	[ebp+eax*4],mm0	;gi[k1]=g1+g3
+	movd	[ebp+ebx*4],mm1	;gi[k2]=g0-g2
+	psrlq	mm1,32		;mm1=[0:g1-g3]
+	movd	[ebp+ecx*4],mm1	;gi[k3]=g1-g3
+	lea	edi,[edi+edx*4]	;fi += k4
+	lea	ebp,[ebp+edx*4]	;gi += k4
+	cmp	edi,esi
+	jc	near .lp31	;}while(fi<fn);
+
+;	<09><><EFBFBD><EFBFBD><EFBFBD>ޤǤ<DEA4>¿ʬO.K.
+
+	mov	fn,esi		;fn=fz+n
+	;<3B><><EFBFBD><EFBFBD><EFBFBD>ͤϰ<CDA4><CFB0><EFBFBD>³<EFBFBD><C2B3><EFBFBD>Ȥ<EFBFBD>
+	;eax=k1,ebx=k2,ecx=k3,edx=k4
+
+	mov	edi,k
+	lea	ebp,[costab_fft+edi*4]
+	mov	ebp,[ebp]	;ebp=t_c
+	mov	[t_c0],ebp
+	mov	[t_c1],ebp	;t_c
+	lea	ebp,[sintab_fft+edi*4]
+	mov	ebp,[ebp]	;ebx=t_s
+	mov	[t_s0],ebp
+	xor	ebp,0x80000000
+	mov	[t_s1],ebp	;-t_s
+
+	movq	mm1,[D_0_1]	;mm1=[0:1]
+	movq	[D_s1c1],mm1	;mm1=[s1:c1]
+	mov	esi,1		;esi=i=1
+
+.lp32:	;	for(i=1;i<kx;i++){
+	movq	mm0,[D_s1c1]	;mm1=[s1:t]=[s1:c1]
+	movq	mm2,mm0
+	pfmul	mm0,[t_c1]	;mm0=[-s1*t_s: t*t_c]
+	pfmul	mm2,[t_s0]	;mm2=[ s1*t_c: t*t_s]
+	pfacc	mm0,mm2		;mm0=[s1:c1]=[ s1*t_c+t*t_s:-s1*t_s+t*t_c]
+	movq	mm2,mm0		;mm2=[s1:c1]
+	movq	[D_s1c1],mm0	;<3B><>¸
+	movq	mm6,mm2
+	punpckldq	mm5,mm6
+	punpckhdq	mm6,mm5	;mm6=[ c1:s1]
+	pxor	mm6,mm7		;mm6=[-c1:s1]
+	movq	[D_Mc1s1],mm6	;<3B><>¸
+	pfmul	mm2,mm2		;mm2=[s1*s1:c1*c1]
+	movq	mm3,mm0		;mm3=[s1:c1]
+	pxor	mm2,mm7		;mm2=[-s1*s1:c1*c1]
+	psrlq	mm3,32		;mm3=[ 0:s1]
+	pfacc	mm2,mm2		;mm2=[c2:c2]=[c1*c1-s1*s1:<]
+	pfmul	mm0,mm3		;mm0=[ 0:c1*s1]
+	pfadd	mm0,mm0		;mm0=[0:s2]=[ 0:2*c1*s1]
+	punpckldq	mm2,mm0	;mm2=[s2:c2]
+	movq	[D_s2c2],mm2	;<3B><>¸
+
+	punpckldq	mm0,mm2
+	punpckhdq	mm2,mm0	;mm2=[c2:s2]
+	pxor	mm2,mm7		;mm2=[-c2:s2]
+	movq	[D_Mc2s2],mm2	;<3B><>¸
+
+	mov	edi,[esp+_P+4]	;edi=fz
+	lea	edi,[edi+esi*4]	;edi=fz+i
+
+	mov	ebp,[esp+_P+4]	;ebp=fz
+	neg	esi		;esi=-i
+	lea	ebp,[ebp+eax*4]	;ebp=fz+k1
+	lea	ebp,[ebp+esi*4]	;ebp=gi=fz+k1-i
+	neg	esi		;esi=i
+
+.lp33:	;	do{ FLOAT a,b,g0,f0,f1,g1,f2,g2,f3,g3;
+
+	movd	mm0,[edi+eax*4]	;mm0=[0:fi_k1]
+	punpckldq	mm0,[ebp+eax*4]	;mm0=[gi_k1:fi_k1]
+	movq	mm1,mm0
+	pfmul	mm0,[D_s2c2]	;mm0=[ s2*gi_k1:c2*fi_k1]
+	pfmul	mm1,[D_Mc2s2]	;mm1=[-c2*gi_k1:s2*fi_k1]
+	pfacc	mm0,mm1		;mm0=[b:a]
+	movd	mm4,[edi]	;mm4=[0:fi_0]
+	movq	mm3,mm0		;mm3=[b:a]
+	punpckldq	mm4,[ebp]	;mm4=[gi_0:fi_0]
+	pfadd	mm3,mm4		;mm3=[g0:f0]=[gi_0+b:fi_0+a]
+	pfsub	mm4,mm0		;mm4=[g1:f1]=[gi_0-b:fi_0-a]
+
+	movd	mm0,[edi+ecx*4]	;mm0=[0:fi_k3]
+	punpckldq	mm0,[ebp+ecx*4]	;mm0=[gi_k3:fi_k3]
+	movq	mm1,mm0
+	pfmul	mm0,[D_s2c2]	;mm0=[ s2*gi_k3:c2*fi_k3]
+	pfmul	mm1,[D_Mc2s2]	;mm1=[-c2*gi_k3:s2*fi_k3]
+	pfacc	mm0,mm1		;mm0=[b:a]
+	movd	mm5,[edi+ebx*4]	;mm5=[0:fi_k2]
+	movq	mm6,mm0		;mm6=[b:a]
+	punpckldq	mm5,[ebp+ebx*4]	;mm5=[gi_k2:fi_k2]
+	pfadd	mm6,mm5		;mm6=[g2:f2]=[gi_k2+b:fi_k2+a]
+	pfsub	mm5,mm0		;mm5=[g3:f3]=[gi_k2-b:fi_k2-a]
+
+	punpckldq	mm1,mm6	;mm1=[f2:*]
+	movq	mm0,[D_s1c1]	;mm0=[s1:c1]
+	punpckhdq	mm1,mm5	;mm1=[g3:f2]
+	pfmul	mm0,mm1		;mm0=[ s1*g3:c1*f2]
+	movq	mm2,[D_Mc1s1]	;mm2=[-c1:s1]
+	pfmul	mm2,mm1		;mm2=[-c1*g3:s1*f2]
+	pfacc	mm0,mm2		;mm0=[b:a]
+
+	punpckldq	mm1,mm3	;mm1=[f0:*]
+	punpckhdq	mm1,mm4	;mm1=[g1:f0]
+	movq	mm2,mm0		;mm2=[b:a]
+	pfadd	mm0,mm1		;mm0=[g1+b:f0+a]
+	pfsubr	mm2,mm1		;mm2=[g1-b:f0-a]
+	movd	[edi],mm0	;fi[0]=f0+a
+	psrlq	mm0,32		;mm0=[0:g1+b]
+	movd	[edi+ebx*4],mm2	;fi[k2]=f0-a
+	psrlq	mm2,32		;mm2=[0:g1-b]
+	movd	[ebp+eax*4],mm0	;gi[k1]=g1+b
+	movd	[ebp+ecx*4],mm2	;gi[k3]=g1-b
+	psrlq	mm6,32		;mm6=[0:g2]
+	movq	mm0,[D_s1c1]	;mm0=[s1:c1]
+	punpckldq	mm5,mm6	;mm5=[g2:f3]
+	pfmul	mm0,mm5		;mm0=[g2* s1:f3*c1]
+	pfmul	mm5,[D_Mc1s1]	;mm5=[g2*-c1:f3*s1]
+	pfacc	mm0,mm5		;mm0=[-b:a]
+	psrlq	mm3,32		;mm3=[0:g0]
+	movq	mm1,mm0		;mm1=[-b:a]
+	punpckldq	mm3,mm4	;mm3=[f1:g0]
+	pfadd	mm0,mm3		;mm0=[f1-b:g0+a]
+	pfsubr	mm1,mm3		;mm1=[f1+b:g0-a]
+	movd	[ebp],mm0	;gi[0]=g0+a
+	psrlq	mm0,32		;mm0=[0:f1-b]
+	movd	[ebp+ebx*4],mm1	;gi[k2]=g0-a
+	psrlq	mm1,32		;mm1=[0:f1+b]
+	movd	[edi+ecx*4],mm0	;fi[k3]=f1-b
+	movd	[edi+eax*4],mm1	;fi[k1]=f1+b
+
+	lea	edi,[edi+edx*4]	;fi += k4
+	lea	ebp,[ebp+edx*4]	;gi += k4
+	cmp	edi,fn
+	jc	near .lp33	;}while(fi<fn)
+	inc	esi
+	cmp	esi,kx
+	jnz	near .lp32	;}
+	cmp	edx,[esp+_P+8]
+	jnz	near .lp30	;}while(k4<n)
+
+
+.exit:
+	add	esp,LOCAL_STACK
+	femms
+	pop	ebp
+	pop	edi
+	pop	esi
+	pop	ebx
+	ret
--- a/lib-src/lame/libmp3lame/i386/fft3dn.nas
+++ b/lib-src/lame/libmp3lame/i386/fft3dn.nas
@@ -0,0 +1,488 @@
+; from a new GOGO-no-coda (1999/09)
+;	Copyright (C) 1999 shigeo
+;	special thanks to Keiichi SAKAI, URURI
+; hacked and back-ported to LAME
+;	 by Takehiro TOMINAGA Nov 2000
+
+%include "nasm.h"
+
+	globaldef fht_3DN
+
+	segment_data
+	align	16
+costab	dd	0x80000000, 0
+	dd	1.414213562,1.414213562
+	dd	9.238795283293805e-01, 9.238795283293805e-01
+	dd	3.826834424611044e-01, 3.826834424611044e-01
+	dd	9.951847264044178e-01, 9.951847264044178e-01
+	dd	9.801714304836734e-02, 9.801714304836734e-02
+	dd	9.996988186794428e-01, 9.996988186794428e-01
+	dd	2.454122920569705e-02, 2.454122920569705e-02
+	dd	9.999811752815535e-01, 9.999811752815535e-01
+	dd	6.135884819898878e-03, 6.135884819898878e-03
+D_1_0_0_0	dd	0.0		, 1.0
+
+	segment_code
+
+PIC_OFFSETTABLE
+
+
+;void fht_3DN(float *fz, int nn);
+
+proc	fht_3DN
+
+	pushd	ebp, ebx, esi, edi
+
+	sub	esp, 20
+
+	call	get_pc.bp
+	add	ebp, PIC_BASE()
+
+	mov	r0, [esp+40]		;fi
+	mov	r1, [esp+44]		;r1 = nn
+	lea	r3, [PIC_EBP_REL(costab)]		;tri = costab
+	lea	r4, [r0+r1*8]		;r4 = fn = &fz[n]
+	mov	[esp+16], r4
+	mov	r4, 8			;kx = k1/2
+
+	pmov	mm7, [r3]
+
+	loopalign 16
+.do1
+	lea	r3, [r3+16]	;tri += 2;
+	pmov	mm6, [PIC_EBP_REL(costab+8)]
+	lea	r2, [r4+r4*2]		;k3*fsize/2
+	mov	r5, 4		;i = 1*fsize
+
+	loopalign 16
+.do2:
+	lea	r1, [r0+r4]		;gi = fi + kx
+	;f
+	pmov	mm0, [r0]	;fi0
+	pmov	mm1, [r0+r4*2]	;fi1
+	pmov	mm2, [r0+r2*2]	;fi3
+	pmov	mm3, [r0+r4*4]	;fi2
+
+	pupldq	mm0, mm0	;fi0 | fi0
+	pupldq	mm1, mm1	;fi1 | fi1
+	pupldq	mm2, mm2	;fi2 | fi2
+	pupldq	mm3, mm3	;fi3 | fi3
+
+	pxor	mm1, mm7	;fi1 | -fi1
+	pxor	mm3, mm7	;fi3 | -fi3
+
+	pfsub	mm0, mm1	;f1 | f0
+	pfsub	mm2, mm3	;f3 | f2
+
+	pmov	mm4, mm0
+	pfadd	mm0, mm2	;f1+f3|f0+f2 = fi1 | fi0
+	pfsub	mm4, mm2	;f1-f3|f0-f2 = fi3 | fi2
+
+	pmovd	[r0], mm0	;fi[0]
+	puphdq	mm0, mm0
+	pmovd	[r0+r4*4], mm4	;fi[k2]
+	puphdq	mm4, mm4
+
+	pmovd	[r0+r4*2], mm4	;fi[k1]
+	pmovd	[r0+r2*2], mm0	;fi[k3]
+	lea	r0, [r0+r4*8]
+
+	;g
+	pmov	mm0, [r1]	;gi0
+	pmov	mm1, [r1+r4*2]	;gi1
+	pmov	mm2, [r1+r4*4]	;gi2
+	pmov	mm3, [r1+r2*2]	;gi3
+
+	pupldq	mm1, mm1
+	pupldq	mm0, mm0	;gi0 | gi0
+	pupldq	mm2, mm3	;gi3 | gi2
+
+	pxor	mm1, mm7	;gi1 | -gi1
+
+	pfsub	mm0, mm1	;gi0-gi1|gi0+gi1 = g1 | g0
+	pfmul	mm2, mm6	;gi3*SQRT2|gi2*SQRT2 = g3 | g2
+
+	pmov	mm4, mm0
+	pfadd	mm0, mm2	;g1+g3|g0+g2 = gi1 | gi0
+	pfsub	mm4, mm2	;g1-g3|g0-g2 = gi3 | gi2
+
+	pmovd	[r1], mm0	;gi[0]
+	puphdq	mm0, mm0
+	pmovd	[r1+r4*4], mm4	;gi[k2]
+	puphdq	mm4, mm4
+
+	cmp	r0, [esp + 16]
+	pmovd	[r1+r4*2], mm0	;gi[k1]
+	pmovd	[r1+r2*2], mm4	;gi[k3]
+
+	jb near .do2
+
+	pmov	mm6, [r3+r5]	; this is not aligned address!!
+
+	loopalign 16
+.for:
+;
+; mm6 = c1 | s1
+; mm7 = 0x800000000 | 0
+;
+	pmov	mm1, mm6
+	mov	r0, [esp+40]	; fz
+	puphdq	mm1, mm1	; c1 | c1
+	lea	r1, [r0+r4*2]
+	pfadd	mm1, mm1	; c1+c1 | c1+c1
+	pfmul	mm1, mm6	; 2*c1*c1 | 2*c1*s1
+	pfsub	mm1, [PIC_EBP_REL(D_1_0_0_0)] ; 2*c1*c1-1.0 | 2*c1*s1 = -c2 | s2
+
+	pmov	mm0, mm1
+	pxor	mm7, mm6	; c1 | -s1
+
+	pupldq	mm2, mm0
+	pupldq	mm3, mm6	; ** | c1
+	puphdq	mm0, mm2	; s2 | c2
+	puphdq	mm6, mm3	;-s1 | c1
+
+	pxor	mm0, [PIC_EBP_REL(costab)]	; c2 | -s2
+
+; mm0 =  s2| c2
+; mm1 = -c2| s2
+; mm6 =  c1| s1
+; mm7 =  s1|-c1 (we use the opposite sign. from GOGO here)
+
+	pmov	[esp], mm0
+	pmov	[esp+8], mm1
+
+	sub	r1, r5		;r1 = gi
+	add	r0, r5		;r0 = fi
+
+	loopalign 16
+.do3:
+	pmov	mm2, [r0+r4*2] ; fi[k1]
+	pmov	mm4, [r1+r4*2] ; gi[k1]
+	pmov	mm3, [r0+r2*2] ; fi[k3]
+	pmov	mm5, [r1+r2*2] ; gi[k3]
+
+	pupldq	mm2, mm2	; fi1 | fi1
+	pupldq	mm4, mm4	; gi1 | gi1
+	pupldq	mm3, mm3	; fi3 | fi3
+	pupldq	mm5, mm5	; gi3 | gi3
+
+	pfmul	mm2, mm0	; s2 * fi1 | c2 * fi1
+	pfmul	mm4, mm1	;-c2 * gi1 | s2 * gi1
+	pfmul	mm3, mm0	; s2 * fi3 | c2 * fi3
+	pfmul	mm5, mm1	;-c2 * gi3 | s2 * gi3
+
+	pfadd	mm2, mm4		;b | a
+	pfadd	mm3, mm5		;d | c
+
+	pmov	mm0, [r0]
+	pmov	mm4, [r1]
+	pmov	mm1, [r0+r4*4]
+	pmov	mm5, [r1+r4*4]
+
+	pupldq	mm0, mm4		;gi0 | fi0
+	pupldq	mm1, mm5		;gi2 | fi2
+
+	pmov	mm4, mm2
+	pmov	mm5, mm3
+
+	pfadd	mm2, mm0		;g0 | f0
+	pfadd	mm3, mm1		;g2 | f2
+
+	pfsub	mm0, mm4		;g1 | f1
+	pfsub	mm1, mm5		;g3 | f3
+
+	pmov	mm4, mm3
+	pmov	mm5, mm1
+
+	pupldq	mm4, mm4		;f2 | f2
+	puphdq	mm5, mm5		;g3 | g3
+	puphdq	mm3, mm3		;g2 | g2
+	pupldq	mm1, mm1		;f3 | f3
+
+	pfmul	mm4, mm6		;f2 * c1 | f2 * s1
+	pfmul	mm5, mm7		;g3 * s1 | g3 *-c1
+	pfmul	mm3, mm6		;g2 * c1 | g2 * s1
+	pfmul	mm1, mm7		;f3 * s1 | f3 *-c1
+
+	pfadd	mm4, mm5		;a | b
+	pfsub	mm3, mm1		;d | c
+
+	pmov	mm5, mm2
+	pmov	mm1, mm0
+
+	pupldq	mm2, mm2		;f0 | f0
+	pupldq	mm0, mm0		;f1 | f1
+
+	puphdq	mm1, mm2		;f0 | g1
+	puphdq	mm5, mm0		;f1 | g0
+
+	pmov	mm2, mm4
+	pmov	mm0, mm3
+
+	pfadd	mm4, mm1		;fi0 | gi1
+	pfadd	mm3, mm5		;fi1 | gi0
+	pfsub	mm1, mm2		;fi2 | gi3
+	pfsub	mm5, mm0		;fi3 | gi2
+
+	pmovd	[r1+r4*2], mm4	;gi[k1]
+	puphdq	mm4, mm4
+	pmovd	[r1], mm3		;gi[0]
+	puphdq	mm3, mm3
+	pmovd	[r1+r2*2], mm1	;gi[k3]
+	puphdq	mm1, mm1
+	pmovd	[r1+r4*4], mm5	;gi[k2]
+	puphdq	mm5, mm5
+
+	pmovd	[r0], mm4	;fi[0]
+	pmovd	[r0+r4*2], mm3	;fi[k1]
+	pmovd	[r0+r4*4], mm1	;fi[k2]
+	pmovd	[r0+r2*2], mm5	;fi[k3]
+
+	lea	r0, [r0+r4*8]
+	lea	r1, [r1+r4*8]
+	cmp	r0, [esp + 16]
+	pmov	mm0, [esp]
+	pmov	mm1, [esp+8]
+
+	jb near	.do3
+
+	add	r5, 4
+; mm6 =  c1| s1
+; mm7 =  s1|-c1 (we use the opposite sign. from GOGO here)
+	pfmul	mm6, [r3]	; c1*a | s1*a
+	pfmul	mm7, [r3+8]	; s1*b |-c1*b
+	cmp	r5, r4
+
+	pfsub	mm6, mm7	; c1*a-s1*b | s1*a+c1*b
+	pupldq	mm7,mm6
+	puphdq	mm6,mm7
+	pmov	mm7, [PIC_EBP_REL(costab)]
+	jb near	.for
+
+	mov	r0, [esp+40]	;fi
+	cmp	r4, [esp+40+4]
+	lea	r4, [r4*4]	;kx *= 4
+
+	jb near	.do1
+.exitttt
+	femms
+	add	esp,20
+	popd	ebp, ebx, esi, edi
+endproc
+
+
+;void fht_E3DN(float *fz, int nn);
+
+proc	fht_E3DN
+
+	pushd	ebp, ebx, esi, edi
+
+	sub	esp, 20
+
+	call	get_pc.bp
+	add	ebp, PIC_BASE()
+
+	mov	r0, [esp+40]		;fi
+	mov	r1, [esp+44]		;r1 = nn
+	lea	r3, [PIC_EBP_REL(costab)]		;tri = costab
+	lea	r4, [r0+r1*8]		;r4 = fn = &fz[n]
+	mov	[esp+16], r4
+	mov	r4, 8			;kx = k1/2
+
+	pmov	mm7, [r3]
+
+	loopalign 16
+.do1
+	lea	r3, [r3+16]	;tri += 2;
+	pmov	mm6, [PIC_EBP_REL(costab+8)]
+	lea	r2, [r4+r4*2]		;k3*fsize/2
+	mov	r5, 4		;i = 1*fsize
+
+	loopalign 16
+.do2:
+	lea	r1, [r0+r4]		;gi = fi + kx
+;f
+	pmov	mm0, [r0]	; X  | fi0
+	pmov	mm1, [r0+r4*4]	; X  | fi2
+	pupldq	mm0, [r0+r4*2]	;fi1 | fi0
+	pupldq	mm1, [r0+r2*2]	;fi3 | fi2
+	pfpnacc	mm0, mm0	;fi0+fi1 | fi0-fi1 = f0|f1
+	pfpnacc	mm1, mm1	;fi2+fi3 | fi2-fi3 = f2|f3
+
+	pmov	mm2, mm0
+	pfadd	mm0, mm1	;f0+f2|f1+f3 = fi0 | fi1
+	pfsub	mm2, mm1	;f0-f2|f1-f3 = fi2 | fi3
+
+	pmovd	[r0+r4*2], mm0	;fi[k1]
+	pmovd	[r0+r2*2], mm2	;fi[k3]
+
+	puphdq	mm0, mm0
+	puphdq	mm2, mm2
+	pmovd	[r0], mm0	;fi[0]
+	pmovd	[r0+r4*4], mm2	;fi[k2]
+
+	lea	r0, [r0+r4*8]
+;g
+	pmov	mm3, [r1]	;    gi0
+	pmov	mm4, [r1+r2*2]	;    gi3
+	pupldq	mm3, [r1+r4*2]	;gi1|gi0
+	pupldq	mm4, [r1+r4*4]	;gi2|gi3
+
+	pfpnacc	mm3, mm3	;gi0+gi1  |gi0-gi1   = f0|f1
+	pfmul	mm4, mm6	;gi2*SQRT2|gi3*SQRT2 = f2|f3
+
+	pmov	mm5, mm3
+	pfadd	mm3, mm4	;f0+f2|f1+f3
+	pfsub	mm5, mm4	;f0-f2|f1-f3
+
+	cmp	r0, [esp + 16]
+	pmovd	[r1+r4*2], mm3	;gi[k1]
+	pmovd	[r1+r2*2], mm5	;gi[k3]
+	puphdq	mm3, mm3
+	puphdq	mm5, mm5
+	pmovd	[r1], mm3	;gi[0]
+	pmovd	[r1+r4*4], mm5	;gi[k2]
+
+	jb near .do2
+
+	pmov	mm6, [r3+r5]	; this is not aligned address!!
+
+	loopalign 16
+.for:
+;
+; mm6 = c1 | s1
+; mm7 = 0x800000000 | 0
+;
+	pmov	mm5, mm6
+	mov	r0, [esp+40]	; fz
+	puphdq	mm5, mm5	; c1 | c1
+	lea	r1, [r0+r4*2]
+	pfadd	mm5, mm5	; c1+c1 | c1+c1
+	pfmul	mm5, mm6	; 2*c1*c1 | 2*c1*s1
+	pfsub	mm5, [PIC_EBP_REL(D_1_0_0_0)] ; 2*c1*c1-1.0 | 2*c1*s1 = -c2 | s2
+
+	pswapd	mm4, mm5	; s2 |-c2
+	pxor	mm4, mm7	; s2 | c2
+	pxor	mm7, mm6	; c1 |-s1
+	pswapd	mm6, mm6	; s1 | c1
+
+; mm4 =  s2| c2
+; mm5 = -c2| s2
+; mm6 =  c1| s1
+; mm7 =  s1|-c1 (we use the opposite sign. from GOGO here)
+
+	pmov	[esp], mm4
+	pmov	[esp+8], mm5
+
+	sub	r1, r5		;r1 = gi
+	add	r0, r5		;r0 = fi
+
+	loopalign 16
+.do3:
+	pmov	mm0, [r0+r2*2] ; fi[k1]
+	pmov	mm2, [r1+r2*2] ; gi[k1]
+	pmov	mm1, [r0+r4*2] ; fi[k3]
+	pmov	mm3, [r1+r4*2] ; gi[k3]
+
+	pupldq	mm0, mm0
+	pupldq	mm2, mm2
+	pupldq	mm1, mm1
+	pupldq	mm3, mm3
+
+	pfmul	mm0, mm4
+	pfmul	mm2, mm5
+	pfmul	mm1, mm4
+	pfmul	mm3, mm5
+
+	pfadd	mm0, mm2		;d | c
+	pfadd	mm1, mm3		;b | a
+
+	pmov	mm2, [r0+r4*4]		;fi2
+	pupldq	mm3, [r1+r4*4]		;gi2 | -
+	pmov	mm4, [r0]		;fi0
+	pupldq	mm5, [r1]		;gi0 | -
+
+	pupldq	mm2, mm0		;c | fi2
+	puphdq	mm3, mm0		;d | gi2
+	pupldq	mm4, mm1		;a | fi0
+	puphdq	mm5, mm1		;b | gi0
+
+	pfpnacc	mm2, mm2		;f2 | f3
+	pfpnacc	mm3, mm3		;g2 | g3
+	pfpnacc	mm4, mm4		;f0 | f1
+	pfpnacc	mm5, mm5		;g0 | g1
+
+	pmov	mm0, mm2
+	pmov	mm1, mm3
+	pupldq	mm2, mm2		;f3 | f3
+	pupldq	mm3, mm3		;g3 | g3
+	puphdq	mm0, mm0		;f2 | f2
+	puphdq	mm1, mm1		;g2 | g2
+
+	pswapd	mm4, mm4		;f1 | f0
+	pswapd	mm5, mm5		;g1 | g0
+
+	pfmul	mm0, mm7		;f2 * s1 | f2 *-c1
+	pfmul	mm3, mm6		;g3 * c1 | g3 * s1
+	pfmul	mm1, mm6		;g2 * c1 | g2 * s1
+	pfmul	mm2, mm7		;f3 * s1 | f3 *-c1
+
+	pfsub	mm0, mm3		; b |-a
+	pfsub	mm1, mm2		; d | c
+
+	pmov	mm2, mm5
+	pmov	mm3, mm4
+	pupldq	mm4, mm0		;-a | f0
+	pupldq	mm5, mm1		; c | g0
+	puphdq	mm2, mm0		; b | g1
+	puphdq	mm3, mm1		; d | f1
+
+	pfpnacc	mm4, mm4		;fi2 | fi0
+	pfpnacc	mm5, mm5		;gi0 | gi2
+	pfpnacc	mm2, mm2		;gi1 | gi3
+	pfpnacc	mm3, mm3		;fi1 | fi3
+
+	pmovd	[r0], mm4		;fi[0]
+	pmovd	[r1+r4*4], mm5		;gi[k2]
+	pmovd	[r1+r2*2], mm2		;gi[k3]
+	pmovd	[r0+r2*2], mm3		;fi[k3]
+
+	puphdq	mm4, mm4
+	puphdq	mm5, mm5
+	puphdq	mm2, mm2
+	puphdq	mm3, mm3
+	pmovd	[r0+r4*4], mm4		;fi[k2]
+	pmovd	[r1], mm5		;gi[0]
+	pmovd	[r1+r4*2], mm2		;gi[k1]
+	pmovd	[r0+r4*2], mm3		;fi[k1]
+
+	lea	r0, [r0+r4*8]
+	lea	r1, [r1+r4*8]
+	cmp	r0, [esp + 16]
+	pmov	mm4, [esp]
+	pmov	mm5, [esp+8]
+
+	jb near	.do3
+
+	add	r5, 4
+; mm6 =  c1| s1
+; mm7 =  s1|-c1 (we use the opposite sign. from GOGO here)
+	pfmul	mm6, [r3]	; c1*a | s1*a
+	pfmul	mm7, [r3+8]	; s1*b |-c1*b
+	cmp	r5, r4
+
+	pfsub	mm6, mm7	; c1*a-s1*b | s1*a+c1*b
+	pswapd	mm6, mm6 ; ???	; s1*a+c1*b | c1*a-s1*b
+	pmov	mm7, [PIC_EBP_REL(costab)]
+	jb near	.for
+
+	mov	r0, [esp+40]	;fi
+	cmp	r4, [esp+40+4]
+	lea	r4, [r4*4]	;kx *= 4
+
+	jb near	.do1
+.exitttt
+	femms
+	add	esp,20
+	popd	ebp, ebx, esi, edi
+endproc
--- a/lib-src/lame/libmp3lame/i386/fftfpu.nas
+++ b/lib-src/lame/libmp3lame/i386/fftfpu.nas
@@ -0,0 +1,619 @@
+; back port from GOGO-no coda 2.24b by Takehiro TOMINAGA
+
+; GOGO-no-coda
+;	Copyright (C) 1999 shigeo
+;	special thanks to URURI
+
+%include "nasm.h"
+
+	externdef costab_fft
+	externdef sintab_fft
+
+	segment_data
+	align 32
+D_1_41421	dd	1.41421356
+D_1_0	dd	1.0
+D_0_5	dd	0.5
+D_0_25	dd	0.25
+D_0_0005	dd	0.0005
+D_0_0	dd	0.0
+
+	segment_code
+
+;void fht(float *fz, int n);
+proc	fht_FPU
+
+%$fz	arg	4
+%$n	arg	4
+
+%$k	local	4
+
+%$f0	local	4
+%$f1	local	4
+%$f2	local	4
+%$f3	local	4
+
+%$g0	local	4
+%$g1	local	4
+%$g2	local	4
+%$g3	local	4
+
+%$s1	local	4
+%$c1	local	4
+%$s2	local	4
+%$c2	local	4
+
+%$t_s	local	4
+%$t_c	local	4
+	alloc
+
+	pushd	ebp, ebx, esi, edi
+
+fht_FPU_1st_part:
+
+fht_FPU_2nd_part:
+
+fht_FPU_3rd_part:
+
+.do_init:
+	mov	r3, 16		;k1*fsize = 4*fsize = k4
+	mov	r4, 8		;kx = k1/2
+	mov	r2, 48		;k3*fsize
+	mov	dword [sp(%$k)], 2	;k = 2
+	mov	r0, [sp(%$fz)]	;fi
+	lea	r1, [r0+8]		;gi = fi + kx
+
+.do:
+.do2:
+	;f
+	fld	dword [r0]
+	fsub	dword [r0+r3]
+
+	fld	dword [r0]
+	fadd	dword [r0+r3]
+
+	fld	dword [r0+r3*2]
+	fsub	dword [r0+r2]
+
+	fld	dword [r0+r3*2]
+	fadd	dword [r0+r2]		;f2 f3 f0 f1
+
+	fld	st2			;f0 f2 f3 f0 f1
+	fadd	st0, st1
+	fstp	dword [r0]		;fi[0]
+
+	fld	st3			;f1 f2 f3 f0 f1
+	fadd	st0, st2
+	fstp	dword [r0+r3]		;fi[k1]
+
+	fsubr	st0, st2		;f0-f2 f3 f0 f1
+	fstp	dword [r0+r3*2]		;fi[k2]
+
+	fsubr	st0, st2		;f1-f3 f0 f1
+	fstp	dword [r0+r2]		;fi[k3]
+	fcompp
+
+	;g
+	fld	dword [r1]
+	fsub	dword [r1+r3]
+
+	fld	dword [r1]
+	fadd	dword [r1+r3]
+
+	fld	dword [D_1_41421]
+	fmul	dword [r1+r2]
+
+	fld	dword [D_1_41421]
+	fmul	dword [r1+r3*2]		;g2 g3 g0 g1
+
+	fld	st2			;g0 g2 g3 g0 g1
+	fadd	st0, st1
+	fstp	dword [r1]		;gi[0]
+
+	fld	st3			;g1 g2 g3 g0 g1
+	fadd	st0, st2
+	fstp	dword [r1+r3]		;gi[k1]
+
+	fsubr	st0, st2		;g0-g2 g3 g0 g1
+	fstp	dword [r1+r3*2]		;gi[k2]
+
+	fsubr	st0, st2		;g1-g3 g0 g1
+	fstp	dword [r1+r2]		;gi[k3]
+	fcompp
+
+	lea	r0, [r0+r3*4]
+	lea	r1, [r1+r3*4]
+	cmp	r0, r6
+	jb	.do2
+
+
+	mov	r0, [sp(%$k)]
+	fld	dword [costab_fft +r0*4]
+	fstp	dword [sp(%$t_c)]
+	fld	dword [sintab_fft +r0*4]
+	fstp	dword [sp(%$t_s)]
+	fld	dword [D_1_0]
+	fstp	dword [sp(%$c1)]
+	fld	dword [D_0_0]
+	fstp	dword [sp(%$s1)]
+
+.for_init:
+	mov	r5, 4		;i = 1*fsize
+
+.for:
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$t_c)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$t_s)]
+	fsubp	st1, st0		;c1
+
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$t_s)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$t_c)]
+	faddp	st1, st0		;s1 c1
+	
+	fld	st1
+	fmul	st0, st0		;c1c1 s1 c1
+	fld	st1
+	fmul	st0, st0		;s1s1 c1c1 s1 c1
+	fsubp	st1, st0		;c2 s1 c1
+	fstp	dword [sp(%$c2)]	;s1 c1
+
+	fld	st1			;c1 s1 c1
+	fmul	st0, st1		;c1s1 s1 c1
+	fadd	st0, st0		;s2 s1 c1
+	fstp	dword [sp(%$s2)]	;s1 c1
+
+	fstp	dword [sp(%$s1)]	;c1
+	fstp	dword [sp(%$c1)]	;
+	
+	mov	r0, [sp(%$fz)]
+	add	r0, r5		;r0 = fi
+	mov	r1, [sp(%$fz)]
+	add	r1, r3
+	sub	r1, r5		;r1 = gi
+
+.do3:
+	fld	dword [sp(%$s2)]
+	fmul	dword [r0+r3]
+	fld	dword [sp(%$c2)]
+	fmul	dword [r1+r3]
+	fsubp	st1, st0		;b = s2*fi[k1] - c2*gi[k1]
+
+	fld	dword [sp(%$c2)]
+	fmul	dword [r0+r3]
+	fld	dword [sp(%$s2)]
+	fmul	dword [r1+r3]
+	faddp	st1, st0		;a = c2*fi[k1] + s2*gi[k1]  b
+
+	fld	dword [r0]
+	fsub	st0, st1		;f1 a b
+	fstp	dword [sp(%$f1)]	;a b
+
+	fadd	dword [r0]		;f0 b
+	fstp	dword [sp(%$f0)]	;b
+
+	fld	dword [r1]
+	fsub	st0, st1		;g1 b
+	fstp	dword [sp(%$g1)]	;b
+
+	fadd	dword [r1]		;g0
+	fstp	dword [sp(%$g0)]	;
+
+
+	fld	dword [sp(%$s2)]
+	fmul	dword [r0+r2]
+	fld	dword [sp(%$c2)]
+	fmul	dword [r1+r2]
+	fsubp	st1, st0		;b = s2*fi[k3] - c2*gi[k3]
+
+	fld	dword [sp(%$c2)]
+	fmul	dword [r0+r2]
+	fld	dword [sp(%$s2)]
+	fmul	dword [r1+r2]
+	faddp	st1, st0		;a = c2*fi[k3] + s2*gi[k3]  b
+
+	fld	dword [r0+r3*2]
+	fsub	st0, st1		;f3 a b
+	fstp	dword [sp(%$f3)]	;a b
+
+	fadd	dword [r0+r3*2]	;f2 b
+	fstp	dword [sp(%$f2)]	;b
+
+	fld	dword [r1+r3*2]
+	fsub	st0, st1		;g3 b
+	fstp	dword [sp(%$g3)]	;b
+
+	fadd	dword [r1+r3*2]	;g2
+	fstp	dword [sp(%$g2)]	;
+
+
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$f2)]
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$g3)]
+	fsubp	st1, st0		;b = s1*f2 - c1*g3
+	
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$f2)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$g3)]
+	faddp	st1, st0		;a = c1*f2 + s1*g3  b
+
+	fld	dword [sp(%$f0)]
+	fsub	st0, st1		;fi[k2] a b
+	fstp	dword [r0+r3*2]
+
+	fadd	dword [sp(%$f0)]	;fi[0] b
+	fstp	dword [r0]
+
+	fld	dword [sp(%$g1)]
+	fsub	st0, st1		;gi[k3] b
+	fstp	dword [r1+r2]
+
+	fadd	dword [sp(%$g1)]	;gi[k1]
+	fstp	dword [r1+r3]
+
+
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$g2)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$f3)]
+	fsubp	st1, st0		;b = c1*g2 - s1*f3
+	
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$g2)]
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$f3)]
+	faddp	st1, st0		;a = s1*g2 + c1*f3  b
+
+	fld	dword [sp(%$g0)]
+	fsub	st0, st1		;gi[k2] a b
+	fstp	dword [r1+r3*2]
+
+	fadd	dword [sp(%$g0)]	;gi[0] b
+	fstp	dword [r1]
+
+	fld	dword [sp(%$f1)]
+	fsub	st0, st1		;fi[k3] b
+	fstp	dword [r0+r2]
+
+	fadd	dword [sp(%$f1)]	;fi[k1]
+	fstp	dword [r0+r3]
+
+
+	lea	r0, [r0+r3*4]
+	lea	r1, [r1+r3*4]
+	cmp	r0, r6
+	jb near	.do3
+
+	add	r5, 4
+	cmp	r5, r4
+	jb near	.for
+
+	cmp	r3, [sp(%$n)]
+	jae	.exit
+
+	add	dword [sp(%$k)], 2	;k  += 2;
+	lea	r3, [r3*4]		;k1 *= 4
+	lea	r2, [r2*4]		;k3 *= 4
+	lea	r4, [r4*4]		;kx *= 4
+	mov	r0, [sp(%$fz)]	;fi
+	lea	r1, [r0+r4]		;gi = fi + kx
+	jmp	.do
+
+.exit:
+	popd	ebp, ebx, esi, edi
+endproc
+
+;*************************************************************
+
+;void fht_FPU_FXCH(float *fz, int n);
+proc	fht_FPU_FXCH
+
+%$fz	arg	4
+%$n	arg	4
+
+%$k	local	4
+
+%$f0	local	4
+%$f1	local	4
+%$f2	local	4
+%$f3	local	4
+
+%$g0	local	4
+%$g1	local	4
+%$g2	local	4
+%$g3	local	4
+
+%$s1	local	4
+%$c1	local	4
+%$s2	local	4
+%$c2	local	4
+
+%$t_s	local	4
+%$t_c	local	4
+	alloc
+
+	pushd	ebp, ebx, esi, edi
+
+fht_FPU_FXCH_1st_part:
+
+fht_FPU_FXCH_2nd_part:
+
+fht_FPU_FXCH_3rd_part:
+
+.do_init:
+	mov	r3, 16		;k1*fsize = 4*fsize = k4
+	mov	r4, 8		;kx = k1/2
+	mov	r2, 48		;k3*fsize
+	mov	dword [sp(%$k)], 2	;k = 2
+	mov	r0, [sp(%$fz)]	;fi
+	lea	r1, [r0+8]		;gi = fi + kx
+
+.do:
+.do2:
+	;f
+	fld	dword [r0]
+	fsub	dword [r0+r3]
+	fld	dword [r0]
+	fadd	dword [r0+r3]
+
+	fld	dword [r0+r3*2]
+	fsub	dword [r0+r2]
+	fld	dword [r0+r3*2]
+	fadd	dword [r0+r2]		;f2 f3 f0 f1
+
+	fld	st3
+	fld	st3
+	fxch	st5
+	fadd	st0, st3
+	fxch	st4
+	fadd	st0, st2
+	fxch	st3
+	fsubp	st1, st0
+	fxch	st1
+	fsubp	st4, st0
+	fxch	st2
+
+	fstp	dword [r0+r3]		;fi[k1]
+	fstp	dword [r0]		;fi[0]
+	fstp	dword [r0+r2]		;fi[k3]
+	fstp	dword [r0+r3*2]		;fi[k2]
+
+	;g
+	fld	dword [r1]
+	fsub	dword [r1+r3]
+	fld	dword [r1]
+	fadd	dword [r1+r3]
+
+	fld	dword [D_1_41421]
+	fmul	dword [r1+r2]
+	fld	dword [D_1_41421]
+	fmul	dword [r1+r3*2]		;g2 g3 g0 g1
+
+	fld	st3
+	fld	st3
+	fxch	st5
+	fadd	st0, st3
+	fxch	st4
+	fadd	st0, st2
+	fxch	st3
+	fsubp	st1, st0
+	fxch	st1
+	fsubp	st4, st0
+	fxch	st2
+
+	fstp	dword [r1+r3]		;gi[k1]
+	fstp	dword [r1]		;gi[0]
+	fstp	dword [r1+r2]		;gi[k3]
+	fstp	dword [r1+r3*2]		;gi[k2]
+
+	lea	r0, [r0+r3*4]
+	lea	r1, [r1+r3*4]
+	cmp	r0, r6
+	jb	.do2
+
+
+	mov	r0, [sp(%$k)]
+	fld	dword [costab_fft +r0*4]
+	fld	dword [sintab_fft +r0*4]
+	fld	dword [D_1_0]
+	fld	dword [D_0_0]
+	fxch	st3
+	fstp	dword [sp(%$t_c)]
+	fxch	st1
+	fstp	dword [sp(%$t_s)]
+	fstp	dword [sp(%$c1)]
+	fstp	dword [sp(%$s1)]
+
+.for_init:
+	mov	r5, 4		;i = 1*fsize
+
+.for:
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$t_c)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$t_s)]
+
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$t_s)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$t_c)]
+	fxch	st2
+	fsubp	st3, st0		;c1
+	faddp	st1, st0		;s1 c1
+	
+	fld	st1
+	fxch	st2
+	fmul	st0, st0		;c1c1 s1 c1
+	fld	st1
+	fxch	st2
+	fmul	st0, st0		;s1s1 c1c1 s1 c1
+
+	fxch	st3
+	fst	dword [sp(%$c1)]	;c1
+	fxch	st2
+	fst	dword [sp(%$s1)]	;s1 c1c1 c1 s1s1
+
+	fmulp	st2, st0
+	fsubrp	st2, st0
+	fadd	st0, st0		;s2 c2
+	fxch	st1
+	fstp	dword [sp(%$c2)]
+	fstp	dword [sp(%$s2)]
+
+	mov	r0, [sp(%$fz)]
+	mov	r1, [sp(%$fz)]
+	add	r0, r5		;r0 = fi
+	add	r1, r3
+	sub	r1, r5		;r1 = gi
+
+.do3:
+	fld	dword [sp(%$s2)]
+	fmul	dword [r0+r3]
+	fld	dword [sp(%$c2)]
+	fmul	dword [r1+r3]
+
+	fld	dword [sp(%$c2)]
+	fmul	dword [r0+r3]
+	fld	dword [sp(%$s2)]
+	fmul	dword [r1+r3]
+	fxch	st2
+	fsubp	st3, st0		;b = s2*fi[k1] - c2*gi[k1]
+	faddp	st1, st0		;a = c2*fi[k1] + s2*gi[k1]  b
+
+	fld	dword [r1]
+	fsub	st0, st2		;g1 a b
+	fxch	st2
+	fadd	dword [r1]		;g0 a g1
+
+	fld	dword [r0]
+	fsub	st0, st2		;f1 g0 a g1
+	fxch	st2
+	fadd	dword [r0]		;f0 g0 f1 g1
+
+	fxch	st3
+	fstp	dword [sp(%$g1)]
+	fstp	dword [sp(%$g0)]
+	fstp	dword [sp(%$f1)]
+	fstp	dword [sp(%$f0)]
+
+
+	fld	dword [sp(%$s2)]
+	fmul	dword [r0+r2]
+	fld	dword [sp(%$c2)]
+	fmul	dword [r1+r2]
+
+	fld	dword [sp(%$c2)]
+	fmul	dword [r0+r2]
+	fld	dword [sp(%$s2)]
+	fmul	dword [r1+r2]
+	fxch	st2
+	fsubp	st3, st0		;b = s2*fi[k3] - c2*gi[k3]
+	faddp	st1, st0		;a = c2*fi[k3] + s2*gi[k3]  b
+
+
+	fld	dword [r1+r3*2]
+	fsub	st0, st2		;g3 a b
+	fxch	st2
+	fadd	dword [r1+r3*2]	;g2 a g3
+
+	fld	dword [r0+r3*2]
+	fsub	st0, st2		;f3 g2 a g3
+	fxch	st2
+	fadd	dword [r0+r3*2]	;f2 g2 f3 g3
+
+	fxch	st3
+	fstp	dword [sp(%$g3)]
+	fstp	dword [sp(%$g2)]
+	fstp	dword [sp(%$f3)]
+	fstp	dword [sp(%$f2)]
+
+
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$f2)]
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$g3)]
+	
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$f2)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$g3)]
+	fxch	st2
+	fsubp	st3, st0		;b = s1*f2 - c1*g3
+	faddp	st1, st0		;a = c1*f2 + s1*g3  b
+
+	fld	dword [sp(%$g1)]
+	fsub	st0, st2		;gi[k3] a b
+	fxch	st2
+	fadd	dword [sp(%$g1)]	;gi[k1] a gi[k3]
+
+	fld	dword [sp(%$f0)]
+	fsub	st0, st2		;fi[k2] gi[k1] a gi[k3]
+	fxch	st2
+	fadd	dword [sp(%$f0)]	;fi[0] gi[k1] fi[k2] gi[k3]
+
+	fxch	st3
+	fstp	dword [r1+r2]
+	fstp	dword [r1+r3]
+	fstp	dword [r0+r3*2]
+	fstp	dword [r0]
+
+
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$g2)]
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$f3)]
+	
+	fld	dword [sp(%$s1)]
+	fmul	dword [sp(%$g2)]
+	fld	dword [sp(%$c1)]
+	fmul	dword [sp(%$f3)]
+	fxch	st2
+	fsubp	st3, st0		;b = c1*g2 - s1*f3
+	faddp	st1, st0		;a = s1*g2 + c1*f3  b
+
+	fld	dword [sp(%$f1)]
+	fsub	st0, st2		;fi[k3] a b
+	fxch	st2
+	fadd	dword [sp(%$f1)]	;fi[k1] a fi[k3]
+
+	fld	dword [sp(%$g0)]
+	fsub	st0, st2		;gi[k2] fi[k1] a fi[k3]
+	fxch	st2
+	fadd	dword [sp(%$g0)]	;gi[0] fi[k1] gi[k2] fi[k3]
+
+	fxch	st3
+	fstp	dword [r0+r2]
+	fstp	dword [r0+r3]
+	fstp	dword [r1+r3*2]
+	fstp	dword [r1]
+
+
+	lea	r0, [r0+r3*4]
+	lea	r1, [r1+r3*4]
+	cmp	r0, r6
+	jb near	.do3
+
+	add	r5, 4
+	cmp	r5, r4
+	jb near	.for
+
+	cmp	r3, [sp(%$n)]
+	jae	.exit
+
+	add	dword [sp(%$k)], 2	;k  += 2;
+	lea	r3, [r3*4]		;k1 *= 4
+	lea	r2, [r2*4]		;k3 *= 4
+	lea	r4, [r4*4]		;kx *= 4
+	mov	r0, [sp(%$fz)]	;fi
+	lea	r1, [r0+r4]		;gi = fi + kx
+	jmp	.do
+
+.exit:
+	popd	ebp, ebx, esi, edi
+endproc
+
+	end
--- a/lib-src/lame/libmp3lame/i386/fftsse.nas
+++ b/lib-src/lame/libmp3lame/i386/fftsse.nas
@@ -0,0 +1,422 @@
+; back port from GOGO-no coda 2.24b by Takehiro TOMINAGA
+
+; GOGO-no-coda
+;	Copyright (C) 1999 shigeo
+;	special thanks to Keiichi SAKAI
+ 
+%include "nasm.h"
+
+	globaldef fht_SSE
+
+	segment_data
+	align 16
+Q_MMPP	dd	0x0,0x0,0x80000000,0x80000000
+Q_MPMP	dd	0x0,0x80000000,0x0,0x80000000
+D_1100	dd 0.0, 0.0, 1.0, 1.0
+costab_fft:
+	dd 9.238795325112867e-01
+	dd 3.826834323650898e-01
+	dd 9.951847266721969e-01
+	dd 9.801714032956060e-02
+	dd 9.996988186962042e-01
+	dd 2.454122852291229e-02
+	dd 9.999811752836011e-01
+	dd 6.135884649154475e-03
+S_SQRT2	dd	1.414213562
+
+	segment_code
+
+PIC_OFFSETTABLE
+
+;------------------------------------------------------------------------
+;	by K. SAKAI
+;	99/08/18	PIII 23k[clk]
+;	99/08/19	̿<><CCBF><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>촹<EFBFBD><ECB4B9> PIII 22k[clk]
+;	99/08/20	bit reversal <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>夫<EFBFBD><E5A4AB><EFBFBD>ܿ<EFBFBD><DCBF><EFBFBD><EFBFBD><EFBFBD> PIII 17k[clk]
+;	99/08/23	<09><><EFBFBD><EFBFBD> unroll PIII 14k[clk]
+;	99/11/12	clean up
+;
+;void fht_SSE(float *fz, int n);
+	align 16
+fht_SSE:
+	push	ebx
+	push	esi
+	push	edi
+	push	ebp
+
+%assign _P 4*5
+
+	;2<><32><EFBFBD>ܤΥ롼<CEA5><EBA1BC>
+	mov	eax,[esp+_P+0]	;eax=fz
+	mov	ebp,[esp+_P+4]	;=n
+	shl	ebp,3
+	add	ebp,eax		; fn  = fz + n, <20><><EFBFBD>δؿ<CEB4><D8BF><EFBFBD>λ<EFBFBD>ޤ<EFBFBD><DEA4><EFBFBD><EFBFBD><EFBFBD>
+	push	ebp
+
+	call	get_pc.bp
+	add	ebp, PIC_BASE()
+
+	lea	ecx,[PIC_EBP_REL(costab_fft)]
+	xor	eax,eax
+	mov	al,8		; =k1=1*(sizeof float)	// 4, 16, 64, 256,...
+.lp2:				; do{
+	mov	esi,[esp+_P+4]	; esi=fi=fz
+	lea	edx,[eax+eax*2]
+	mov	ebx, esi
+
+; <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>2<EFBFBD><32><EFBFBD>󤷤<EFBFBD><F3A4B7A4><EFBFBD><EFBFBD>ԤǤ<D4A4><C7A4>ʤ<EFBFBD><CAA4><EFBFBD>ʬ<EFBFBD><CAAC>FPU<50>Τۤ<CEA4><DBA4><EFBFBD>®<EFBFBD><C2AE><EFBFBD><EFBFBD>
+	loopalign	16
+.lp20:				; do{
+;                       f0     = fi[0 ] + fi[k1];
+;                       f2     = fi[k2] + fi[k3];
+;                       f1     = fi[0 ] - fi[k1];
+;                       f3     = fi[k2] - fi[k3];
+;                       fi[0 ] = f0     + f2;
+;                       fi[k1] = f1     + f3;
+;                       fi[k2] = f0     - f2;
+;                       fi[k3] = f1     - f3;
+	lea	edi,[ebx+eax]	; edi=gi=fi+ki/2
+	fld	dword [ebx]
+	fadd	dword [ebx+eax*2]
+	fld	dword [ebx+eax*4]
+	fadd	dword [ebx+edx*2]
+
+	fld	dword [ebx]
+	fsub	dword [ebx+eax*2]
+	fld	dword [ebx+eax*4]
+	fsub	dword [ebx+edx*2]
+
+	fld	st1
+	fadd	st0,st1
+	fstp	dword [ebx+eax*2]
+	fsubp	st1,st0
+	fstp	dword [ebx+edx*2]
+
+	fld	st1
+	fadd	st0,st1
+	fstp	dword [ebx]
+	fsubp	st1,st0
+	fstp	dword [ebx+eax*4]
+
+	lea	ebx,[ebx + eax*8]	; = fi += (k1 * 4);
+;                       g0     = gi[0 ] + gi[k1];
+;                       g2     = SQRT2  * gi[k2];
+;                       g1     = gi[0 ] - gi[k1];
+;                       g3     = SQRT2  * gi[k3];
+;                       gi[0 ] = g0     + g2;
+;                       gi[k2] = g0     - g2;
+;                       gi[k1] = g1     + g3;
+;                       gi[k3] = g1     - g3;
+	fld	dword [edi]
+	fadd	dword [edi+eax*2]
+	fld	dword [PIC_EBP_REL(S_SQRT2)]
+	fmul	dword [edi+eax*4]
+
+	fld	dword [edi]
+	fsub	dword [edi+eax*2]
+	fld	dword [PIC_EBP_REL(S_SQRT2)]
+	fmul	dword [edi+edx*2]
+
+	fld	st1
+	fadd	st0,st1
+	fstp	dword [edi+eax*2]
+	fsubp	st1,st0
+	fstp	dword [edi+edx*2]
+
+	fld	st1
+	fadd	st0,st1
+	fstp	dword [edi]
+	fsubp	st1,st0
+	fstp	dword [edi+eax*4]
+
+	cmp	ebx,[esp]
+	jl	near .lp20		; while (fi<fn);
+
+
+;               i = 1; //for (i=1;i<kx;i++){
+;                       c1 = 1.0*t_c - 0.0*t_s;
+;                       s1 = 0.0*t_c + 1.0*t_s;
+	movlps	xmm6,[ecx] ; = { --,  --,  s1, c1}
+	movaps	xmm7,xmm6
+
+	shufps	xmm6,xmm6,R4(0,1,1,0)	; = {+c1, +s1, +s1, +c1} -> ɬ<><C9AC>
+;                       c2 = c1*c1 - s1*s1 = 1 - (2*s1)*s1;
+;                       s2 = c1*s1 + s1*c1 = 2*s1*c1;
+	shufps	xmm7,xmm7,R4(1,0,0,1)
+	movss	xmm5,xmm7		; = { --,  --,  --, s1}
+	xorps	xmm7,[PIC_EBP_REL(Q_MMPP)]	; = {-s1, -c1, +c1, +s1} -> ɬ<><C9AC>
+
+	addss	xmm5,xmm5		; = (--, --,  --, 2*s1)
+	add	esi,4		; esi = fi = fz + i
+	shufps	xmm5,xmm5,R4(0,0,0,0)	; = (2*s1, 2*s1, 2*s1, 2*s1)
+	mulps	xmm5,xmm6		; = (2*s1*c1, 2*s1*s1, 2*s1*s1, 2*s1*c1)
+	subps	xmm5,[PIC_EBP_REL(D_1100)]		; = (--, 2*s1*s1-1, --, 2*s1*c1) = {-- -c2 -- s2}
+	movaps	xmm4,xmm5
+	shufps	xmm5,xmm5,R4(2,0,2,0)	; = {-c2, s2, -c2, s2} -> ɬ<><C9AC>
+
+	xorps	xmm4,[PIC_EBP_REL(Q_MMPP)]		; = {--, c2, --, s2}
+	shufps	xmm4,xmm4,R4(0,2,0,2)	; = {s2, c2, s2, c2} -> ɬ<><C9AC>
+
+	loopalign	16
+.lp21:				; do{
+;                               a       = c2*fi[k1] + s2*gi[k1];
+;                               b       = s2*fi[k1] - c2*gi[k1];
+;                               c       = c2*fi[k3] + s2*gi[k3];
+;                               d       = s2*fi[k3] - c2*gi[k3];
+;                               f0      = fi[0 ]        + a;
+;                               g0      = gi[0 ]        + b;
+;                               f2      = fi[k1 * 2]    + c;
+;                               g2      = gi[k1 * 2]    + d;
+;                               f1      = fi[0 ]        - a;
+;                               g1      = gi[0 ]        - b;
+;                               f3      = fi[k1 * 2]    - c;
+;                               g3      = gi[k1 * 2]    - d;
+	lea	edi,[esi + eax*2 - 8]	; edi = gi = fz +k1-i
+
+	movss	xmm0,[esi + eax*2]	; = fi[k1]
+	movss	xmm2,[esi + edx*2]	; = fi[k3]
+	shufps	xmm0,xmm2,0x00	; = {fi[k3], fi[k3], fi[k1], fi[k1]}
+	movss	xmm1,[edi + eax*2]	; = fi[k1]
+	movss	xmm3,[edi + edx*2]	; = fi[k3]
+	shufps	xmm1,xmm3,0x00	; = {gi[k3], gi[k3], gi[k1], gi[k1]}
+	movss	xmm2,[esi]		; = fi[0]
+	mulps	xmm0,xmm4		; *= {+s2, +c2, +s2, +c2}
+	movss	xmm3,[esi + eax*4]	; = fi[k2]
+	unpcklps	xmm2,xmm3	; = {--, --, fi[k2], fi[0]}
+	mulps	xmm1,xmm5		; *= {-c2, +s2, -c2, +s2}
+	movss	xmm3,[edi + eax*4]	; = gi[k2]
+	addps	xmm0,xmm1		; = {d, c, b, a}
+	movss	xmm1,[edi]		; = gi[0]
+	unpcklps	xmm1,xmm3	; = {--,  --, gi[k2], gi[0]}
+	unpcklps	xmm2,xmm1	; = {gi[k2], fi[k2], gi[0], fi[0]}
+	movaps	xmm1,xmm2
+	addps	xmm1,xmm0	; = {g2, f2, g0, f0}
+	subps	xmm2,xmm0	; = {g3, f3, g1, f1}
+
+;                               a       = c1*f2     + s1*g3;
+;                               c       = s1*g2     + c1*f3;
+;                               b       = s1*f2     - c1*g3;
+;                               d       = c1*g2     - s1*f3;
+;                               fi[0 ]  = f0        + a;
+;                               gi[0 ]  = g0        + c;
+;                               gi[k1]  = g1        + b;
+;                               fi[k1]  = f1        + d;
+;                               fi[k1 * 2]  = f0    - a;
+;                               gi[k1 * 2]  = g0    - c;
+;                               gi[k3]      = g1    - b;
+;                               fi[k3]      = f1    - d;
+	movaps	xmm3,xmm1
+	movhlps	xmm1,xmm1	; = {g2, f2, g2, f2}
+	shufps	xmm3,xmm2,0x14	; = {f1, g1, g0, f0}
+	mulps	xmm1,xmm6	; *= {+c1, +s1, +s1, +c1}
+	shufps	xmm2,xmm2,0xBB	; = {f3, g3, f3, g3}
+	mulps	xmm2,xmm7	; *= {-s1, -c1, +c1, +s1}
+	addps	xmm1,xmm2	; = {d, b, c, a}
+	movaps	xmm2,xmm3
+	addps	xmm3,xmm1	; = {fi[k1], gi[k1], gi[0], fi[0]}
+	subps	xmm2,xmm1	; = {fi[k3], gi[k3], gi[k1*2], fi[k1*2]}
+	movhlps	xmm0,xmm3
+	movss	[esi],xmm3
+	shufps	xmm3,xmm3,0x55
+	movss	[edi+eax*2],xmm0
+	shufps	xmm0,xmm0,0x55
+	movss	[edi],xmm3
+	movss	[esi+eax*2],xmm0
+	movhlps	xmm0,xmm2
+	movss	[esi+eax*4],xmm2
+	shufps	xmm2,xmm2,0x55
+	movss	[edi+edx*2],xmm0
+	shufps	xmm0,xmm0,0x55
+	movss	[edi+eax*4],xmm2
+	movss	[esi+edx*2],xmm0
+	lea	esi,[esi + eax*8] ; fi += (k1 * 4);
+	cmp	esi,[esp]
+	jl	near .lp21		; while (fi<fn);
+
+
+; unroll<6C><6C><EFBFBD><EFBFBD>do loop<6F><70>43+4̿<34><CCBF>
+
+; <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ǤϤʤ<CFA4>for<6F>롼<EFBFBD>פ<EFBFBD>i=2<><32><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>unrolling<6E><67><EFBFBD><EFBFBD>
+; kx=   2,   8,  32,  128
+; k4=  16,  64, 256, 1024
+;       0, 6/2,30/2,126/2
+
+	xor	ebx,ebx
+	mov	bl, 4*2		; = i = 4
+	cmp	ebx,eax		; i < k1
+	jnl	near .F22
+;               for (i=2;i<kx;i+=2){
+	loopalign	16
+.lp22:
+; at here, xmm6 is {c3, s3, s3, c3}
+;                       c1 = c3*t_c - s3*t_s;
+;                       s1 = c3*t_s + s3*t_c;
+	movlps	xmm0,[ecx]
+	shufps	xmm0,xmm0,R4(1,1,0,0)	; = {t_s, t_s, t_c, t_c}
+	mulps	xmm6,xmm0	; = {c3*ts, s3*ts, s3*tc, c3*tc}
+	movhlps	xmm4,xmm6	; = {--,    --,    c3*ts, s3*ts}
+	xorps	xmm4,[PIC_EBP_REL(Q_MPMP)]	; = {--,    --,   -c3*ts, s3*ts}
+	subps	xmm6,xmm4	; = {-,-, c3*ts+s3*tc, c3*tc-s3*ts}={-,-,s1,c1}
+
+;                       c3 = c1*t_c - s1*t_s;
+;                       s3 = s1*t_c + c1*t_s;
+	shufps	xmm6,xmm6,0x14	; = {c1, s1, s1, c1}
+	mulps	xmm0,xmm6	; = {ts*c1 ts*s1 tc*s1 tc*c1}
+	movhlps	xmm3,xmm0
+	xorps	xmm3,[PIC_EBP_REL(Q_MPMP)]
+	subps	xmm0,xmm3	; = {--, --, s3, c3}
+
+; {s2 s4 c4 c2} = {2*s1*c1 2*s3*c3 1-2*s3*s3 1-2*s1*s1}
+	unpcklps	xmm6,xmm0	; xmm6 = {s3, s1, c3, c1}
+	movaps	xmm7, xmm6
+	shufps	xmm6,xmm6,R4(2,3,1,0)	; xmm6 = {s1, s3, c3, c1}
+	addps	xmm7, xmm7		; {s3*2, s1*2,   --,   --}
+	mov	edi,[esp+_P+4]		; = fz
+	shufps	xmm7, xmm7, R4(2,3,3,2)	; {s1*2, s3*2, s3*2, s1*2}
+	sub	edi,ebx			; edi = fz - i/2
+	mulps	xmm7, xmm6		; {s1*s1*2, s3*s3*2, s3*c3*2, s1*c1*2}
+	lea	esi,[edi + ebx*2]	; esi = fi = fz +i/2
+	subps	xmm7, [PIC_EBP_REL(D_1100)]		; {-c2, -c4, s4, s2}
+	lea	edi,[edi + eax*2-4]	; edi = gi = fz +k1-i/2
+
+;                       fi = fz +i;
+;                       gi = fz +k1-i;
+;                       do{
+.lp220:
+; unroll<6C><6C><EFBFBD><EFBFBD>do loop<6F><70>51+4̿<34><CCBF>
+;                               a       = c2*fi[k1  ] + s2*gi[k1  ];
+;                               e       = c4*fi[k1+1] + s4*gi[k1-1];
+;                               f       = s4*fi[k1+1] - c4*gi[k1-1];
+;                               b       = s2*fi[k1  ] - c2*gi[k1  ];
+;                               c       = c2*fi[k3  ] + s2*gi[k3  ];
+;                               g       = c4*fi[k3+1] + s4*gi[k3-1];
+;                               h       = s4*fi[k3+1] - c4*gi[k3-1];
+;                               d       = s2*fi[k3  ] - c2*gi[k3  ];
+
+	movaps	xmm4,xmm7	; = {-c2 -c4  s4  s2}
+	xorps	xmm4,[PIC_EBP_REL(Q_MMPP)]	; = { c2  c4  s4  s2}
+	shufps	xmm4,xmm4,0x1B	; = { s2  s4  c4  c2}
+	movlps	xmm0,[esi+eax*2]
+	movlps	xmm1,[edi+eax*2]
+	movlps	xmm2,[esi+edx*2]
+	movlps	xmm3,[edi+edx*2]
+	shufps	xmm0,xmm0,0x14
+	shufps	xmm1,xmm1,0x41
+	shufps	xmm2,xmm2,0x14
+	shufps	xmm3,xmm3,0x41
+	mulps	xmm0,xmm4
+	mulps	xmm1,xmm7
+	mulps	xmm2,xmm4
+	mulps	xmm3,xmm7
+	addps	xmm0,xmm1	; xmm0 = {b, f, e, a}
+	addps	xmm2,xmm3	; xmm2 = {d, h, g, c}
+;17
+
+;                               f0      = fi[0   ]    + a;
+;                               f4      = fi[0 +1]    + e;
+;                               g4      = gi[0 -1]    + f;
+;                               g0      = gi[0   ]    + b;
+;                               f1      = fi[0   ]    - a;
+;                               f5      = fi[0 +1]    - e;
+;                               g5      = gi[0 -1]    - f;
+;                               g1      = gi[0   ]    - b;
+;                               f2      = fi[k2  ]    + c;
+;                               f6      = fi[k2+1]    + g;
+;                               g6      = gi[k2-1]    + h;
+;                               g2      = gi[k2  ]    + d;
+;                               f3      = fi[k2  ]    - c;
+;                               f7      = fi[k2+1]    - g;
+;                               g7      = gi[k2-1]    - h;
+;                               g3      = gi[k2  ]    - d;
+	movlps	xmm1,[esi      ]
+	movhps	xmm1,[edi      ]
+	movaps	xmm4,xmm1
+	subps	xmm1,xmm0	; xmm1 = {g1, g5, f5, f1}
+	movlps	xmm3,[esi+eax*4]
+	movhps	xmm3,[edi+eax*4]
+	movaps	xmm5,xmm3
+	subps	xmm3,xmm2	; xmm3 = {g3, g7, f7, f3}
+	addps	xmm0,xmm4	; xmm0 = {g0, g4, f4, f0}
+	addps	xmm2,xmm5	; xmm2 = {g2, g6, f6, f2}
+;10
+
+;                               a       = c1*f2     + s1*g3;	<09><>*<2A><> + <20><>*<2A><>
+;                               e       = c3*f6     + s3*g7;
+;                               g       = s3*g6     + c3*f7;
+;                               c       = s1*g2     + c1*f3;
+;                               d       = c1*g2     - s1*f3;	<09><>*<2A><> - <20><>*<2A><>
+;                               h       = c3*g6     - s3*f7;
+;                               f       = s3*f6     - c3*g7;
+;                               b       = s1*f2     - c1*g3;
+
+	movaps	xmm5,xmm6	; xmm6 = {s1, s3, c3, c1}
+	shufps	xmm5,xmm5,0x1B	; = {c1, c3, s3, s1}
+	movaps	xmm4,xmm2
+	mulps	xmm4,xmm6
+	shufps	xmm2,xmm2,0x1B	; xmm2 = {f2, f6, g6, g2}
+	mulps	xmm2,xmm6
+	mulps	xmm5,xmm3
+	mulps	xmm3,xmm6
+	shufps	xmm3,xmm3,0x1B
+	addps	xmm4,xmm3	; = {c, g, e, a}
+	subps	xmm2,xmm5	; = {b, f, h, d}
+;10
+
+;                               fi[0   ]  = f0        + a;
+;                               fi[0 +1]  = f4        + e;
+;                               gi[0 -1]  = g4        + g;
+;                               gi[0   ]  = g0        + c;
+;                               fi[k2  ]  = f0        - a;
+;                               fi[k2+1]  = f4        - e;
+;                               gi[k2-1]  = g4        - g;
+;                               gi[k2  ]  = g0        - c;
+;                               fi[k1  ]  = f1        + d;
+;                               fi[k1+1]  = f5        + h;
+;                               gi[k1-1]  = g5        + f;
+;                               gi[k1  ]  = g1        + b;
+;                               fi[k3  ]  = f1        - d;
+;                               fi[k3+1]  = f5        - h;
+;                               gi[k3-1]  = g5        - f;
+;                               gi[k3  ]  = g1        - b;
+	movaps	xmm3,xmm0
+	subps	xmm0,xmm4
+	movlps	[esi+eax*4],xmm0
+	movhps	[edi+eax*4],xmm0
+	addps	xmm4,xmm3
+	movlps	[esi      ],xmm4
+	movhps	[edi      ],xmm4
+
+	movaps	xmm5,xmm1
+	subps	xmm1,xmm2
+	movlps	[esi+edx*2],xmm1
+	movhps	[edi+edx*2],xmm1
+	addps	xmm2,xmm5
+	movlps	[esi+eax*2],xmm2
+	movhps	[edi+eax*2],xmm2
+; 14
+;                               gi     += k4;
+;                               fi     += k4;
+	lea	edi,[edi + eax*8] ; gi += (k1 * 4);
+	lea	esi,[esi + eax*8] ; fi += (k1 * 4);
+	cmp	esi,[esp]
+	jl	near .lp220		; while (fi<fn);
+;                       } while (fi<fn);
+
+	add	ebx,byte 2*4	; i+= 4
+	cmp	ebx,eax		; i < k1
+	shufps	xmm6,xmm6,R4(1,2,2,1)	; (--,s3,c3,--) => {c3, s3, s3, c3}
+	jl	near .lp22
+;               }
+.F22:
+	shl	eax,2
+	add	ecx, byte 8
+	cmp	eax,[esp+_P+8]	; while ((k1 * 4)<n);
+	jle	near .lp2
+	pop	ebp
+	pop	ebp
+	pop	edi
+	pop	esi
+	pop	ebx
+	ret
+
+	end
--- a/lib-src/lame/libmp3lame/i386/ffttbl.nas
+++ b/lib-src/lame/libmp3lame/i386/ffttbl.nas
@@ -0,0 +1,78 @@
+
+;	for new GOGO-no-coda (1999/09)
+;	Copyright (C) 1999 shigeo
+;	special thanks to URURI, Keiichi SAKAI
+
+
+;	fft sin,cos,gray<61>ơ<EFBFBD><C6A1>֥<EFBFBD>
+;	99/08/21
+;	99/09/01(<28><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>)<29><><EFBFBD>ӥå<D3A5>ȿž<C8BF>ơ<EFBFBD><C6A1>֥<EFBFBD><D6A5><EFBFBD><EFBFBD><EFBFBD>
+;	99/09/14 <20><><EFBFBD>쥤<EFBFBD><ECA5A4><EFBFBD><EFBFBD><EFBFBD>ɥ<EFBFBD><C9A5><EFBFBD><EFBFBD>ǥå<C7A5><C3A5><EFBFBD>ɽ<EFBFBD><C9BD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Х벽
+
+%include "nasm.h"
+
+	globaldef	costab_fft
+	globaldef	sintab_fft
+	globaldef	gray_index
+
+	segment_data
+	align 16
+
+costab_fft:
+	dd 0.000000000000
+	dd 0.707106781187
+	dd 0.923879532511
+	dd 0.980785280403
+	dd 0.995184726672
+	dd 0.998795456205
+	dd 0.999698818696
+	dd 0.999924701839
+	dd 0.999981175283
+	dd 0.999995293810
+	dd 0.999998823452
+	dd 0.999999705863
+	dd 0.999999926466
+	dd 0.999999981616
+	dd 0.999999995404
+	dd 0.999999998851
+
+sintab_fft:
+	dd 1.000000000000
+	dd 0.707106781187
+	dd 0.382683432365
+	dd 0.195090322016
+	dd 0.098017140330
+	dd 0.049067674327
+	dd 0.024541228523
+	dd 0.012271538286
+	dd 0.006135884649
+	dd 0.003067956763
+	dd 0.001533980186
+	dd 0.000766990319
+	dd 0.000383495188
+	dd 0.000191747597
+	dd 0.000095873799
+	dd 0.000047936900
+
+		align 16
+gray_index:
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 7
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 8
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 7
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 9
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 7
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 8
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 7
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 6
+		db	2, 3, 2, 4, 2, 3, 2, 5, 2, 3, 2, 4, 2, 3, 2, 10
+
+	segment_code
+
+	end
--- a/lib-src/lame/libmp3lame/i386/nasm.h
+++ b/lib-src/lame/libmp3lame/i386/nasm.h
@@ -0,0 +1,268 @@
+
+;	Copyright (C) 1999 URURI
+
+;	nasm<EFBFBD>ѥޥ<EFBFBD><EFBFBD><EFBFBD>
+;	1999/08/21 <EFBFBD><EFBFBD><EFBFBD>
+;	1999/10/10 <EFBFBD><EFBFBD><EFBFBD>Ĥ<EFBFBD><EFBFBD>ɲ<EFBFBD>
+;	1999/10/27 aout<EFBFBD>б<EFBFBD>
+;	1999/11/07 pushf, popf <EFBFBD><EFBFBD>NASM<EFBFBD>ΥХ<EFBFBD><EFBFBD>б<EFBFBD>
+;	1999/12/02 for BCC ( Thanks to Miquel )
+
+; for Windows Visual C++        -> define WIN32
+;             Borland or cygwin ->        WIN32 and COFF
+; for FreeBSD 2.x               ->        AOUT
+; for TownsOS                   ->        __tos__
+; otherwise                     ->   none
+
+;̾<EFBFBD><EFBFBD><EFBFBD><EFBFBD>դ<EFBFBD><EFBFBD><EFBFBD>
+
+BITS 32
+
+section .note.GNU-stack noalloc noexec nowrite progbits
+
+%ifdef YASM
+	%define segment_code segment .text align=16 use32
+	%define segment_data segment .data align=16 use32
+	%define segment_bss  segment .bss align=16 use32
+%elifdef WIN32
+	%define segment_code segment .text align=16 class=CODE use32
+	%define segment_data segment .data align=16 class=DATA use32
+%ifdef __BORLANDC__
+	%define segment_bss  segment .data align=16 class=DATA use32
+%else
+	%define segment_bss  segment .bss align=16 class=DATA use32
+%endif
+%elifdef AOUT
+	%define _NAMING
+	%define segment_code segment .text
+	%define segment_data segment .data
+	%define segment_bss  segment .bss
+%else
+%ifidn __OUTPUT_FORMAT__,elf
+	section .note.GNU-stack progbits noalloc noexec nowrite align=1
+%endif
+	%define segment_code segment .text align=16 class=CODE use32
+	%define segment_data segment .data align=16 class=DATA use32
+	%define segment_bss  segment .bss align=16 class=DATA use32
+%endif
+
+%ifdef WIN32
+	%define _NAMING
+%endif
+
+%ifdef __tos__
+group CGROUP text
+group DGROUP data
+%endif
+
+;ñ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ư<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
+
+%idefine float dword
+%idefine fsize 4
+%idefine fsizen(a) (fsize*(a))
+
+;<EFBFBD><EFBFBD>ɷ<EFBFBD><EFBFBD>
+
+%idefine wsize 2
+%idefine wsizen(a) (wsize*(a))
+%idefine dwsize 4
+%idefine dwsizen(a) (dwsize*(a))
+
+;REG
+
+%define r0 eax
+%define r1 ebx
+%define r2 ecx
+%define r3 edx
+%define r4 esi
+%define r5 edi
+%define r6 ebp
+%define r7 esp
+
+;MMX,3DNow!,SSE
+
+%define pmov	movq
+%define pmovd	movd
+
+%define pupldq	punpckldq
+%define puphdq	punpckhdq
+%define puplwd	punpcklwd
+%define puphwd	punpckhwd
+
+%define xm0 xmm0
+%define xm1 xmm1
+%define xm2 xmm2
+%define xm3 xmm3
+%define xm4 xmm4
+%define xm5 xmm5
+%define xm6 xmm6
+%define xm7 xmm7
+
+;<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>åե<EFBFBD><EFBFBD>Ѥ<EFBFBD>4<EFBFBD>ʥޥ<EFBFBD><EFBFBD><EFBFBD>
+
+%define R4(a,b,c,d) (a*64+b*16+c*4+d)
+
+;C<EFBFBD>饤<EFBFBD><EFBFBD><EFBFBD>ʴʰץޥ<EFBFBD><EFBFBD><EFBFBD>
+
+%imacro globaldef 1
+	%ifdef _NAMING
+		%define %1 _%1
+	%endif
+	global %1
+%endmacro
+
+%imacro externdef 1
+	%ifdef _NAMING
+		%define %1 _%1
+	%endif
+	extern %1
+%endmacro
+
+%imacro proc 1
+	%push	proc
+	%ifdef _NAMING
+		global _%1
+	%else
+		global %1
+	%endif
+
+	align 32
+%1:
+_%1:
+
+	%assign %$STACK 0
+	%assign %$STACKN 0
+	%assign %$ARG 4
+%endmacro
+
+%imacro endproc 0
+	%ifnctx proc
+		%error expected 'proc' before 'endproc'.
+	%else
+		%if %$STACK > 0
+			add esp, %$STACK
+		%endif
+
+		%if %$STACK <> (-%$STACKN)
+			%error STACKLEVEL mismatch check 'local', 'alloc', 'pushd', 'popd'
+		%endif
+
+		ret
+		%pop
+	%endif
+%endmacro
+
+%idefine sp(a) esp+%$STACK+a
+
+%imacro arg 1
+	%00	equ %$ARG
+	%assign %$ARG %$ARG+%1
+%endmacro
+
+%imacro local 1
+	%assign %$STACKN %$STACKN-%1
+	%00 equ %$STACKN
+%endmacro
+
+%imacro alloc 0
+	sub esp, (-%$STACKN)-%$STACK
+	%assign %$STACK (-%$STACKN)
+%endmacro
+
+%imacro pushd 1-*
+	%rep %0
+		push %1
+		%assign %$STACK %$STACK+4
+	%rotate 1
+	%endrep
+%endmacro
+
+%imacro popd 1-*
+	%rep %0
+	%rotate -1
+		pop %1
+		%assign %$STACK %$STACK-4
+	%endrep
+%endmacro
+
+; bug of NASM-0.98
+%define pushf db 0x66, 0x9C
+%define popf  db 0x66, 0x9D
+
+%define	ge16(n)		((((n) / 16)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge15(n)		((((n) / 15)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge14(n)		((((n) / 14)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge13(n)		((((n) / 13)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge12(n)		((((n) / 12)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge11(n)		((((n) / 11)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge10(n)		((((n) / 10)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge9(n)		((((n) /  9)*0xFFFFFFFF) & 0xFFFFFFFF)
+%define	ge8(n)		(ge9(n) | ((((n) /  8)*0xFFFFFFFF) & 0xFFFFFFFF))
+%define	ge7(n)		(ge9(n) | ((((n) /  7)*0xFFFFFFFF) & 0xFFFFFFFF))
+%define	ge6(n)		(ge9(n) | ((((n) /  6)*0xFFFFFFFF) & 0xFFFFFFFF))
+%define	ge5(n)		(ge9(n) | ((((n) /  5)*0xFFFFFFFF) & 0xFFFFFFFF))
+%define	ge4(n)		(ge5(n) | ((((n) /  4)*0xFFFFFFFF) & 0xFFFFFFFF))
+%define	ge3(n)		(ge5(n) | ((((n) /  3)*0xFFFFFFFF) & 0xFFFFFFFF))
+%define	ge2(n)		(ge3(n) | ((((n) /  2)*0xFFFFFFFF) & 0xFFFFFFFF))
+%define	ge1(n)		(ge2(n) | ((((n) /  1)*0xFFFFFFFF) & 0xFFFFFFFF))
+
+; macro to align for begining of loop
+; %1   does not align if it LE bytes to next alignment 
+;      4..16 
+;      default is 12
+
+%imacro	loopalignK6	0-1 12 
+%%here:
+	times (($$-%%here) & 15 & ge1(($$-%%here) & 15) & ~ge4(($$-%%here) & 15)) nop
+	times (1                & ge4(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) jmp short %%skip
+	times (((($$-%%here) & 15)-2) & ge4(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) nop
+%%skip:
+%endmacro
+
+%imacro	loopalignK7	0-1 12 
+%%here:
+	times (1 & ge1(($$-%%here) & 15)  & ~ge2(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) nop
+	times (1 & ge2(($$-%%here) & 15)  & ~ge3(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) DB 08Bh,0C0h
+	times (1 & ge3(($$-%%here) & 15)  & ~ge4(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) DB 08Dh,004h,020h
+	times (1 & ge4(($$-%%here) & 15)  & ~ge5(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) DB 08Dh,044h,020h,000h
+	times (1 & ge5(($$-%%here) & 15)  & ~ge6(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) DB 08Dh,044h,020h,000h,090h
+	times (1 & ge6(($$-%%here) & 15)  & ~ge7(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) DB 08Dh,080h,0,0,0,0
+	times (1 & ge7(($$-%%here) & 15)  & ~ge8(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) DB 08Dh,004h,005h,0,0,0,0
+	times (1 & ge8(($$-%%here) & 15)  & ~ge9(($$-%%here) & 15)  & ~ge%1(($$-%%here) & 15)) DB 08Dh,004h,005h,0,0,0,0,90h
+	times (1 & ge9(($$-%%here) & 15)  & ~ge10(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) DB 0EBh,007h,90h,90h,90h,90h,90h,90h,90h
+	times (1 & ge10(($$-%%here) & 15) & ~ge11(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) DB 0EBh,008h,90h,90h,90h,90h,90h,90h,90h,90h
+	times (1 & ge11(($$-%%here) & 15) & ~ge12(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) DB 0EBh,009h,90h,90h,90h,90h,90h,90h,90h,90h,90h
+	times (1 & ge12(($$-%%here) & 15) & ~ge13(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) DB 0EBh,00Ah,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h
+	times (1 & ge13(($$-%%here) & 15) & ~ge14(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) DB 0EBh,00Bh,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h
+	times (1 & ge14(($$-%%here) & 15) & ~ge15(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) DB 0EBh,00Ch,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h
+	times (1 & ge15(($$-%%here) & 15) & ~ge16(($$-%%here) & 15) & ~ge%1(($$-%%here) & 15)) DB 0EBh,00Dh,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h,90h
+%%skip:
+%endmacro
+
+%imacro	loopalign	0-1 12 
+	loopalignK7 %1
+%endmacro
+%define PACK(x,y,z,w)	(x*64+y*16+z*4+w)
+
+%ifidn __OUTPUT_FORMAT__,elf
+
+%idefine PIC_BASE(A) _GLOBAL_OFFSET_TABLE_ + $$ - $ wrt ..gotpc
+%idefine PIC_EBP_REL(A) ebp + A wrt ..gotoff
+%macro PIC_OFFSETTABLE 0
+extern  _GLOBAL_OFFSET_TABLE_
+get_pc.bp:
+	mov ebp, [esp]
+	retn
+%endmacro
+
+%else
+
+%define PIC_BASE(A) (0)
+%define PIC_EBP_REL(A) (A)
+%macro PIC_OFFSETTABLE 0
+get_pc.bp:
+	mov ebp, [esp]
+	retn
+%endmacro
+
+%endif
--- a/lib-src/lame/libmp3lame/i386/scalar.nas
+++ b/lib-src/lame/libmp3lame/i386/scalar.nas